LICENSE
MANIFEST.in
README.md
setup.py
opencompass/__init__.py
opencompass/registry.py
opencompass.egg-info/PKG-INFO
opencompass.egg-info/SOURCES.txt
opencompass.egg-info/dependency_links.txt
opencompass.egg-info/entry_points.txt
opencompass.egg-info/requires.txt
opencompass.egg-info/top_level.txt
opencompass/cli/__init__.py
opencompass/cli/main.py
opencompass/configs/dataset_collections/chat_OC15.py
opencompass/configs/datasets/ARC_Prize_Public_Evaluation/README.md
opencompass/configs/datasets/ARC_Prize_Public_Evaluation/arc_prize_public_evaluation_gen.py
opencompass/configs/datasets/ARC_Prize_Public_Evaluation/arc_prize_public_evaluation_gen_872059.py
opencompass/configs/datasets/ARC_Prize_Public_Evaluation/arc_prize_public_evaluation_gen_fedd04.py
opencompass/configs/datasets/ARC_c/ARC_c_clean_ppl.py
opencompass/configs/datasets/ARC_c/ARC_c_cot_gen_926652.py
opencompass/configs/datasets/ARC_c/ARC_c_few_shot_gen_e9b043.py
opencompass/configs/datasets/ARC_c/ARC_c_few_shot_ppl.py
opencompass/configs/datasets/ARC_c/ARC_c_gen.py
opencompass/configs/datasets/ARC_c/ARC_c_gen_1e0de5.py
opencompass/configs/datasets/ARC_c/ARC_c_ppl.py
opencompass/configs/datasets/ARC_c/ARC_c_ppl_2ef631.py
opencompass/configs/datasets/ARC_c/ARC_c_ppl_a450bd.py
opencompass/configs/datasets/ARC_c/ARC_c_ppl_d52a21.py
opencompass/configs/datasets/ARC_e/ARC_e_gen.py
opencompass/configs/datasets/ARC_e/ARC_e_gen_1e0de5.py
opencompass/configs/datasets/ARC_e/ARC_e_ppl.py
opencompass/configs/datasets/ARC_e/ARC_e_ppl_2ef631.py
opencompass/configs/datasets/ARC_e/ARC_e_ppl_a450bd.py
opencompass/configs/datasets/ARC_e/ARC_e_ppl_d52a21.py
opencompass/configs/datasets/CARDBiomedBench/CARDBiomedBench_llmjudge_gen_99a231.py
opencompass/configs/datasets/CHARM/README.md
opencompass/configs/datasets/CHARM/README_ZH.md
opencompass/configs/datasets/CHARM/charm_memory_gen_bbbd53.py
opencompass/configs/datasets/CHARM/charm_memory_settings.py
opencompass/configs/datasets/CHARM/charm_reason_cot_only_gen_f7b7d3.py
opencompass/configs/datasets/CHARM/charm_reason_gen.py
opencompass/configs/datasets/CHARM/charm_reason_gen_f8fca2.py
opencompass/configs/datasets/CHARM/charm_reason_ppl_3da4de.py
opencompass/configs/datasets/CHARM/charm_reason_settings.py
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Anachronisms_Judgment_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Anachronisms_Judgment_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Anachronisms_Judgment_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Anachronisms_Judgment_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Movie_and_Music_Recommendation_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Movie_and_Music_Recommendation_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Movie_and_Music_Recommendation_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Movie_and_Music_Recommendation_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Natural_Language_Inference_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Natural_Language_Inference_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Natural_Language_Inference_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Natural_Language_Inference_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Reading_Comprehension_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Reading_Comprehension_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Reading_Comprehension_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Reading_Comprehension_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sequence_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sequence_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sequence_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sequence_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sport_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sport_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sport_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Sport_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Time_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Time_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Time_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Chinese_Time_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Anachronisms_Judgment_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Anachronisms_Judgment_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Anachronisms_Judgment_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Anachronisms_Judgment_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Movie_and_Music_Recommendation_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Movie_and_Music_Recommendation_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Movie_and_Music_Recommendation_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Movie_and_Music_Recommendation_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Natural_Language_Inference_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Natural_Language_Inference_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Natural_Language_Inference_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Natural_Language_Inference_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Reading_Comprehension_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Reading_Comprehension_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Reading_Comprehension_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Reading_Comprehension_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sequence_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sequence_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sequence_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sequence_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sport_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sport_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sport_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Sport_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Time_Understanding_Direct.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Time_Understanding_EN-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Time_Understanding_XLT.txt
opencompass/configs/datasets/CHARM/few-shot-examples/Global_Time_Understanding_ZH-CoT.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Anachronisms_Judgment_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Movie_and_Music_Recommendation_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Natural_Language_Inference_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Reading_Comprehension_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Sequence_Understanding_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Sport_Understanding_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Chinese_Time_Understanding_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Anachronisms_Judgment_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Movie_and_Music_Recommendation_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Natural_Language_Inference_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Reading_Comprehension_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Sequence_Understanding_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Sport_Understanding_Translate-EN.txt
opencompass/configs/datasets/CHARM/few-shot-examples_Translate-EN/Global_Time_Understanding_Translate-EN.txt
opencompass/configs/datasets/CIBench/CIBench_generation_gen_8ab0dc.py
opencompass/configs/datasets/CIBench/CIBench_generation_oracle_gen_c4a7c1.py
opencompass/configs/datasets/CIBench/CIBench_template_gen_e6b12a.py
opencompass/configs/datasets/CIBench/CIBench_template_oracle_gen_fecda1.py
opencompass/configs/datasets/CLUE_C3/CLUE_C3_gen.py
opencompass/configs/datasets/CLUE_C3/CLUE_C3_gen_8c358f.py
opencompass/configs/datasets/CLUE_C3/CLUE_C3_ppl.py
opencompass/configs/datasets/CLUE_C3/CLUE_C3_ppl_56b537.py
opencompass/configs/datasets/CLUE_C3/CLUE_C3_ppl_e24a31.py
opencompass/configs/datasets/CLUE_CMRC/CLUE_CMRC_gen.py
opencompass/configs/datasets/CLUE_CMRC/CLUE_CMRC_gen_1bd3c8.py
opencompass/configs/datasets/CLUE_CMRC/CLUE_CMRC_gen_3749cd.py
opencompass/configs/datasets/CLUE_CMRC/CLUE_CMRC_gen_8484b9.py
opencompass/configs/datasets/CLUE_CMRC/CLUE_CMRC_gen_941108.py
opencompass/configs/datasets/CLUE_DRCD/CLUE_DRCD_gen.py
opencompass/configs/datasets/CLUE_DRCD/CLUE_DRCD_gen_1bd3c8.py
opencompass/configs/datasets/CLUE_DRCD/CLUE_DRCD_gen_3749cd.py
opencompass/configs/datasets/CLUE_DRCD/CLUE_DRCD_gen_8484b9.py
opencompass/configs/datasets/CLUE_DRCD/CLUE_DRCD_gen_941108.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_gen.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_gen_901306.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_ppl.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_ppl_378c5b.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_ppl_6507d7.py
opencompass/configs/datasets/CLUE_afqmc/CLUE_afqmc_ppl_7b0c1e.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_gen.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_gen_1abf97.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_gen_51e956.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_ppl.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_ppl_98dd6e.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_ppl_ef69e7.py
opencompass/configs/datasets/CLUE_cmnli/CLUE_cmnli_ppl_fdc6de.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_gen.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_gen_51e956.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_gen_c4cb6c.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_ppl.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_ppl_98dd6e.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_ppl_ef69e7.py
opencompass/configs/datasets/CLUE_ocnli/CLUE_ocnli_ppl_fdc6de.py
opencompass/configs/datasets/ChemBench/ChemBench_gen.py
opencompass/configs/datasets/ChemBench/ChemBench_gen_a9f753.py
opencompass/configs/datasets/ChemBench/ChemBench_llmjudge_gen.py
opencompass/configs/datasets/ChemBench/ChemBench_llmjudge_gen_c584cf.py
opencompass/configs/datasets/ClimaQA/ClimaQA_Gold_llm_judge_gen.py
opencompass/configs/datasets/ClimaQA/ClimaQA_Gold_llm_judge_gen_f15343.py
opencompass/configs/datasets/ClimaQA/ClimaQA_Silver_llm_judge_gen.py
opencompass/configs/datasets/ClimaQA/ClimaQA_Silver_llm_judge_gen_f15343.py
opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen.py
opencompass/configs/datasets/ClinicBench/ClinicBench_llmjudge_gen_d09668.py
opencompass/configs/datasets/Earth_Silver/Earth_Silver_gen.py
opencompass/configs/datasets/Earth_Silver/Earth_Silver_llmjudge_gen.py
opencompass/configs/datasets/Earth_Silver/Earth_Silver_llmjudge_gen_46140c.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_gen.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_gen_634f41.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_ppl.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_ppl_4b16c0.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_ppl_9ef540.py
opencompass/configs/datasets/FewCLUE_bustm/FewCLUE_bustm_ppl_e53034.py
opencompass/configs/datasets/FewCLUE_chid/FewCLUE_chid_gen.py
opencompass/configs/datasets/FewCLUE_chid/FewCLUE_chid_gen_0a29a2.py
opencompass/configs/datasets/FewCLUE_chid/FewCLUE_chid_ppl.py
opencompass/configs/datasets/FewCLUE_chid/FewCLUE_chid_ppl_8f2872.py
opencompass/configs/datasets/FewCLUE_chid/FewCLUE_chid_ppl_acccb5.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_gen.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_gen_c68933.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_ppl.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_ppl_12e4e0.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_ppl_4284a0.py
opencompass/configs/datasets/FewCLUE_cluewsc/FewCLUE_cluewsc_ppl_868415.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_gen.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_gen_28b223.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_gen_87f4a8.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_ppl.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_ppl_769f8d.py
opencompass/configs/datasets/FewCLUE_csl/FewCLUE_csl_ppl_841b62.py
opencompass/configs/datasets/FewCLUE_eprstmt/FewCLUE_eprstmt_gen.py
opencompass/configs/datasets/FewCLUE_eprstmt/FewCLUE_eprstmt_gen_740ea0.py
opencompass/configs/datasets/FewCLUE_eprstmt/FewCLUE_eprstmt_ppl.py
opencompass/configs/datasets/FewCLUE_eprstmt/FewCLUE_eprstmt_ppl_1ce587.py
opencompass/configs/datasets/FewCLUE_eprstmt/FewCLUE_eprstmt_ppl_f1e631.py
opencompass/configs/datasets/FewCLUE_ocnli_fc/FewCLUE_ocnli_fc_gen.py
opencompass/configs/datasets/FewCLUE_ocnli_fc/FewCLUE_ocnli_fc_gen_f97a97.py
opencompass/configs/datasets/FewCLUE_ocnli_fc/FewCLUE_ocnli_fc_ppl.py
opencompass/configs/datasets/FewCLUE_ocnli_fc/FewCLUE_ocnli_fc_ppl_9e8b3d.py
opencompass/configs/datasets/FewCLUE_ocnli_fc/FewCLUE_ocnli_fc_ppl_c08300.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_gen.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_gen_b90e4a.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_ppl.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_ppl_7d1c07.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_ppl_d10e8a.py
opencompass/configs/datasets/FewCLUE_tnews/FewCLUE_tnews_ppl_fff486.py
opencompass/configs/datasets/FinanceIQ/FinanceIQ_gen.py
opencompass/configs/datasets/FinanceIQ/FinanceIQ_gen_e0e6b5.py
opencompass/configs/datasets/FinanceIQ/FinanceIQ_ppl.py
opencompass/configs/datasets/FinanceIQ/FinanceIQ_ppl_42b9bd.py
opencompass/configs/datasets/GLUE_CoLA/GLUE_CoLA_ppl.py
opencompass/configs/datasets/GLUE_CoLA/GLUE_CoLA_ppl_77d0df.py
opencompass/configs/datasets/GLUE_MRPC/GLUE_MRPC_ppl.py
opencompass/configs/datasets/GLUE_MRPC/GLUE_MRPC_ppl_96564c.py
opencompass/configs/datasets/GLUE_QQP/GLUE_QQP_ppl.py
opencompass/configs/datasets/GLUE_QQP/GLUE_QQP_ppl_250d00.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_gen.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_gen_5cfe9e.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_mixed.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_mixed_9af5ee.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_no_subjective_gen_4c31db.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_no_subjective_gen_d16acb.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_no_subjective_gen_d21e37.py
opencompass/configs/datasets/GaokaoBench/GaokaoBench_prompts.py
opencompass/configs/datasets/GaokaoBench/README.md
opencompass/configs/datasets/HLE/hle_biomed_llm_verify_gen_6ff468.py
opencompass/configs/datasets/HLE/hle_gen.py
opencompass/configs/datasets/HLE/hle_llmverify_academic.py
opencompass/configs/datasets/HLE/hle_llmverify_gen_6ff468.py
opencompass/configs/datasets/HealthBench/healthbench_gen_831613.py
opencompass/configs/datasets/IFEval/IFEval.md
opencompass/configs/datasets/IFEval/IFEval_gen.py
opencompass/configs/datasets/IFEval/IFEval_gen_3321a3.py
opencompass/configs/datasets/IFEval/IFEval_gen_353ae7.py
opencompass/configs/datasets/IFEval/README.md
opencompass/configs/datasets/LCBench/README.md
opencompass/configs/datasets/LCBench/lcbench_gen.py
opencompass/configs/datasets/LCBench/lcbench_gen_5ff288.py
opencompass/configs/datasets/LCBench/lcbench_levels_gen_bb665f.py
opencompass/configs/datasets/LCBench/lcbench_repeat10_gen.py
opencompass/configs/datasets/LCBench/lcbench_repeat10_gen_5ff288.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_gen.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_gen_326684.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_ppl.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_ppl_d2333a.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_zero_shot_gen.py
opencompass/configs/datasets/MMLUArabic/MMLUArabic_zero_shot_gen_3523e0.py
opencompass/configs/datasets/MMLUArabic/README.md
opencompass/configs/datasets/MathBench/deprecated_mathbench_2024_gen_de9ff9.py
opencompass/configs/datasets/MathBench/deprecated_mathbench_agent_gen_48ec47.py
opencompass/configs/datasets/MathBench/deprecated_mathbench_agent_gen_fbe13b.py
opencompass/configs/datasets/MathBench/deprecated_mathbench_arith_gen_ccd638.py
opencompass/configs/datasets/MathBench/deprecated_mathbench_cot_gen_66f329.py
opencompass/configs/datasets/MathBench/deprecated_mathbench_gen_7b734b.py
opencompass/configs/datasets/MathBench/mathbench_2024_few_shot_mixed_4a3fd4.py
opencompass/configs/datasets/MathBench/mathbench_2024_gen_19e486.py
opencompass/configs/datasets/MathBench/mathbench_2024_gen_1dc21d.py
opencompass/configs/datasets/MathBench/mathbench_2024_gen_4b8f28.py
opencompass/configs/datasets/MathBench/mathbench_2024_gen_50a320.py
opencompass/configs/datasets/MathBench/mathbench_2024_gen_fc2a24.py
opencompass/configs/datasets/MathBench/mathbench_2024_wocircular_gen_1dc21d.py
opencompass/configs/datasets/MathBench/mathbench_2024_wocircular_mixed_8eb12b.py
opencompass/configs/datasets/MathBench/mathbench_gen.py
opencompass/configs/datasets/MathBench/mathbench_prompt.py
opencompass/configs/datasets/MedBench/medbench_gen.py
opencompass/configs/datasets/MedBench/medbench_gen_0b4fff.py
opencompass/configs/datasets/MedCalc_Bench/MedCalcBench_official_gen_a5155f.py
opencompass/configs/datasets/MedQA/MedQA_gen_3bf756.py
opencompass/configs/datasets/MedQA/MedQA_llmjudge_gen_3bf756.py
opencompass/configs/datasets/MedXpertQA/MedXpertQA_gen.py
opencompass/configs/datasets/MedXpertQA/MedXpertQA_llmjudge_gen.py
opencompass/configs/datasets/Medbullets/medbullets_gen.py
opencompass/configs/datasets/Medbullets/medbullets_gen_60c8f5.py
opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen.py
opencompass/configs/datasets/Medbullets/medbullets_llmjudge_gen_60c8f5.py
opencompass/configs/datasets/NPHardEval/NPHardEval_gen.py
opencompass/configs/datasets/NPHardEval/NPHardEval_gen_22aac5.py
opencompass/configs/datasets/NPHardEval/README.md
opencompass/configs/datasets/OlymMATH/README.md
opencompass/configs/datasets/OlymMATH/olymmath_cascade_eval_gen_97b203.py
opencompass/configs/datasets/OlymMATH/olymmath_llm_judeg_gen.py
opencompass/configs/datasets/OlymMATH/olymmath_llmverify_gen_97b203.py
opencompass/configs/datasets/OlympiadBench/OlympiadBenchMath_0shot_llmverify_gen_9c22f2.py
opencompass/configs/datasets/OlympiadBench/OlympiadBench_0shot_cascade_eval_gen_be8b13.py
opencompass/configs/datasets/OlympiadBench/OlympiadBench_0shot_gen_be8b13.py
opencompass/configs/datasets/OlympiadBench/OlympiadBench_0shot_llmverify_gen_be8b13.py
opencompass/configs/datasets/OlympiadBench/OlympiadBench_categories.py
opencompass/configs/datasets/OpenFinData/OpenFinData_gen.py
opencompass/configs/datasets/OpenFinData/OpenFinData_gen_46dedb.py
opencompass/configs/datasets/OpenFinData/README.md
opencompass/configs/datasets/PHYBench/phybench_gen.py
opencompass/configs/datasets/PHYSICS/PHYSICS_llm_judge_gen.py
opencompass/configs/datasets/PHYSICS/PHYSICS_llm_judge_gen_a133a2.py
opencompass/configs/datasets/PJExam/PJExam_gen.py
opencompass/configs/datasets/PJExam/PJExam_gen_8cd97c.py
opencompass/configs/datasets/PMMEval/flores_gen.py
opencompass/configs/datasets/PMMEval/flores_gen_2697d7.py
opencompass/configs/datasets/PMMEval/humanevalxl_gen.py
opencompass/configs/datasets/PMMEval/humanevalxl_gen_bdec92.py
opencompass/configs/datasets/PMMEval/mgsm_gen.py
opencompass/configs/datasets/PMMEval/mgsm_gen_679720.py
opencompass/configs/datasets/PMMEval/mhellaswag_gen.py
opencompass/configs/datasets/PMMEval/mhellaswag_gen_1a6b73.py
opencompass/configs/datasets/PMMEval/mifeval_gen.py
opencompass/configs/datasets/PMMEval/mifeval_gen_79f8fb.py
opencompass/configs/datasets/PMMEval/mlogiqa_gen.py
opencompass/configs/datasets/PMMEval/mlogiqa_gen_36c4f9.py
opencompass/configs/datasets/PMMEval/mmmlu_gen.py
opencompass/configs/datasets/PMMEval/mmmlu_gen_d5017d.py
opencompass/configs/datasets/PMMEval/pmmeval_gen.py
opencompass/configs/datasets/PMMEval/xnli_gen.py
opencompass/configs/datasets/PMMEval/xnli_gen_973734.py
opencompass/configs/datasets/ProteinLMBench/ProteinLMBench_gen_a67965.py
opencompass/configs/datasets/ProteinLMBench/ProteinLMBench_llmjudge_gen_a67965.py
opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen.py
opencompass/configs/datasets/PubMedQA/PubMedQA_llmjudge_gen_f00302.py
opencompass/configs/datasets/QuALITY/QuALITY.md
opencompass/configs/datasets/QuALITY/QuALITY_gen.py
opencompass/configs/datasets/QuALITY/QuALITY_gen_c407cb.py
opencompass/configs/datasets/R_Bench/R-Bench.md
opencompass/configs/datasets/R_Bench/rbench_gen_544610.py
opencompass/configs/datasets/R_Bench/rbench_llmjudge_gen_c89350.py
opencompass/configs/datasets/SVAMP/svamp_gen.py
opencompass/configs/datasets/SVAMP/svamp_gen_fb25e4.py
opencompass/configs/datasets/SciEval/SciEval_5shot_gen_4043d4.py
opencompass/configs/datasets/SciEval/SciEval_5shot_llmjudge_gen_b7b684.py
opencompass/configs/datasets/SciEval/SciEval_lifescience_sets.py
opencompass/configs/datasets/SciKnowEval/SciKnowEval_gen_ebe47d.py
opencompass/configs/datasets/SciKnowEval/SciKnowEval_llmjudge_gen_ebe47d.py
opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen.py
opencompass/configs/datasets/ScienceQA/ScienceQA_llmjudge_gen_f00302.py
opencompass/configs/datasets/SimpleQA/README.md
opencompass/configs/datasets/SimpleQA/simpleqa_gen.py
opencompass/configs/datasets/SimpleQA/simpleqa_gen_0283c3.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_0shot_instruct_gen.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_fts_0shot_instruct.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_fts_gen_5774b5.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_gen.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_meteor_0shot_instruct.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_meteor_gen_065150.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_nc_0shot_instruct.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_nc_gen_c84c18.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_pp_acc_0_shot_instruct.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_pp_acc_gen_8607a3.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_rmse_0shot_instruct.py
opencompass/configs/datasets/SmolInstruct/smolinstruct_rmse_gen_0fcc6b.py
opencompass/configs/datasets/SuperGLUE_AX_b/SuperGLUE_AX_b_gen.py
opencompass/configs/datasets/SuperGLUE_AX_b/SuperGLUE_AX_b_gen_4dfefa.py
opencompass/configs/datasets/SuperGLUE_AX_b/SuperGLUE_AX_b_ppl.py
opencompass/configs/datasets/SuperGLUE_AX_b/SuperGLUE_AX_b_ppl_0748aa.py
opencompass/configs/datasets/SuperGLUE_AX_b/SuperGLUE_AX_b_ppl_6db806.py
opencompass/configs/datasets/SuperGLUE_AX_g/SuperGLUE_AX_g_gen.py
opencompass/configs/datasets/SuperGLUE_AX_g/SuperGLUE_AX_g_gen_68aac7.py
opencompass/configs/datasets/SuperGLUE_AX_g/SuperGLUE_AX_g_ppl.py
opencompass/configs/datasets/SuperGLUE_AX_g/SuperGLUE_AX_g_ppl_50f8f6.py
opencompass/configs/datasets/SuperGLUE_AX_g/SuperGLUE_AX_g_ppl_66caf3.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_cot_gen_1d56df.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_few_shot_gen_ba58ea.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_few_shot_ppl.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_gen.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_gen_883d50.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl_16b1d9.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl_314797.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl_314b96.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl_4da4db.py
opencompass/configs/datasets/SuperGLUE_BoolQ/SuperGLUE_BoolQ_ppl_9619db.py
opencompass/configs/datasets/SuperGLUE_CB/SuperGLUE_CB_gen.py
opencompass/configs/datasets/SuperGLUE_CB/SuperGLUE_CB_gen_854c6c.py
opencompass/configs/datasets/SuperGLUE_CB/SuperGLUE_CB_ppl.py
opencompass/configs/datasets/SuperGLUE_CB/SuperGLUE_CB_ppl_0143fe.py
opencompass/configs/datasets/SuperGLUE_CB/SuperGLUE_CB_ppl_11c175.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_gen.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_gen_91ca53.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_ppl.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_ppl_54058d.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_ppl_5c24f1.py
opencompass/configs/datasets/SuperGLUE_COPA/SuperGLUE_COPA_ppl_9f3618.py
opencompass/configs/datasets/SuperGLUE_MultiRC/SuperGLUE_MultiRC_gen.py
opencompass/configs/datasets/SuperGLUE_MultiRC/SuperGLUE_MultiRC_gen_27071f.py
opencompass/configs/datasets/SuperGLUE_MultiRC/SuperGLUE_MultiRC_ppl.py
opencompass/configs/datasets/SuperGLUE_MultiRC/SuperGLUE_MultiRC_ppl_866273.py
opencompass/configs/datasets/SuperGLUE_MultiRC/SuperGLUE_MultiRC_ppl_ced824.py
opencompass/configs/datasets/SuperGLUE_RTE/SuperGLUE_RTE_gen.py
opencompass/configs/datasets/SuperGLUE_RTE/SuperGLUE_RTE_gen_68aac7.py
opencompass/configs/datasets/SuperGLUE_RTE/SuperGLUE_RTE_ppl.py
opencompass/configs/datasets/SuperGLUE_RTE/SuperGLUE_RTE_ppl_50f8f6.py
opencompass/configs/datasets/SuperGLUE_RTE/SuperGLUE_RTE_ppl_66caf3.py
opencompass/configs/datasets/SuperGLUE_ReCoRD/SuperGLUE_ReCoRD_gen.py
opencompass/configs/datasets/SuperGLUE_ReCoRD/SuperGLUE_ReCoRD_gen_0f7784.py
opencompass/configs/datasets/SuperGLUE_ReCoRD/SuperGLUE_ReCoRD_gen_30dea0.py
opencompass/configs/datasets/SuperGLUE_ReCoRD/SuperGLUE_ReCoRD_gen_a69961.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_gen.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_gen_7902a7.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_gen_fe4bf3.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_ppl.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_ppl_003529.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_ppl_1c4a90.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_ppl_d0f531.py
opencompass/configs/datasets/SuperGLUE_WSC/SuperGLUE_WSC_ppl_f37e78.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_gen.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_gen_d06864.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_ppl.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_ppl_312de9.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_ppl_3fb6fd.py
opencompass/configs/datasets/SuperGLUE_WiC/SuperGLUE_WiC_ppl_c926be.py
opencompass/configs/datasets/TabMWP/TabMWP_gen.py
opencompass/configs/datasets/TabMWP/TabMWP_gen_2aef96.py
opencompass/configs/datasets/TheoremQA/README.md
opencompass/configs/datasets/TheoremQA/TheoremQA_5shot_gen_6f0af8.py
opencompass/configs/datasets/TheoremQA/TheoremQA_few_shot_examples.py
opencompass/configs/datasets/TheoremQA/TheoremQA_few_shot_examples_official.py
opencompass/configs/datasets/TheoremQA/TheoremQA_gen.py
opencompass/configs/datasets/TheoremQA/ThroremQA_0shot_cot_gen_8acdf7.py
opencompass/configs/datasets/TheoremQA/deprecated_TheoremQA_gen_424e0a.py
opencompass/configs/datasets/TheoremQA/deprecated_TheoremQA_gen_7009de.py
opencompass/configs/datasets/TheoremQA/deprecated_TheoremQA_gen_ef26ca.py
opencompass/configs/datasets/TheoremQA/deprecated_TheoremQA_post_v2_gen_2c2583.py
opencompass/configs/datasets/TheoremQA/deprecated_TheoremQA_post_v2_gen_ef26ca.py
opencompass/configs/datasets/XCOPA/XCOPA_ppl.py
opencompass/configs/datasets/XCOPA/XCOPA_ppl_54058d.py
opencompass/configs/datasets/XLSum/XLSum_gen.py
opencompass/configs/datasets/XLSum/XLSum_gen_2bb71c.py
opencompass/configs/datasets/Xsum/Xsum_gen.py
opencompass/configs/datasets/Xsum/Xsum_gen_31397e.py
opencompass/configs/datasets/Xsum/Xsum_gen_8ea5f8.py
opencompass/configs/datasets/adv_glue/__init__.py
opencompass/configs/datasets/adv_glue/adv_glue_mnli/adv_glue_mnli_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_mnli/adv_glue_mnli_gen_bd8ef0.py
opencompass/configs/datasets/adv_glue/adv_glue_mnli_mm/adv_glue_mnli_mm_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_mnli_mm/adv_glue_mnli_mm_gen_bd8ef0.py
opencompass/configs/datasets/adv_glue/adv_glue_qnli/adv_glue_qnli_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_qnli/adv_glue_qnli_gen_0b7326.py
opencompass/configs/datasets/adv_glue/adv_glue_qqp/adv_glue_qqp_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_qqp/adv_glue_qqp_gen_cdc277.py
opencompass/configs/datasets/adv_glue/adv_glue_rte/adv_glue_rte_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_rte/adv_glue_rte_gen_8cc547.py
opencompass/configs/datasets/adv_glue/adv_glue_sst2/adv_glue_sst2_gen.py
opencompass/configs/datasets/adv_glue/adv_glue_sst2/adv_glue_sst2_gen_ee8d3b.py
opencompass/configs/datasets/agieval/agieval_gen.py
opencompass/configs/datasets/agieval/agieval_gen_397d81.py
opencompass/configs/datasets/agieval/agieval_gen_617738.py
opencompass/configs/datasets/agieval/agieval_gen_64afd3.py
opencompass/configs/datasets/agieval/agieval_gen_a0c741.py
opencompass/configs/datasets/agieval/agieval_mixed.py
opencompass/configs/datasets/agieval/agieval_mixed_0fa998.py
opencompass/configs/datasets/aime2024/README.md
opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_gen_2b9dc2.py
opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_academic_gen.py
opencompass/configs/datasets/aime2024/aime2024_0shot_nocot_genericllmeval_gen_2b9dc2.py
opencompass/configs/datasets/aime2024/aime2024_cascade_eval_gen_5e9f4f.py
opencompass/configs/datasets/aime2024/aime2024_gen.py
opencompass/configs/datasets/aime2024/aime2024_gen_17d799.py
opencompass/configs/datasets/aime2024/aime2024_gen_6e39a4.py
opencompass/configs/datasets/aime2024/aime2024_llmjudge_gen.py
opencompass/configs/datasets/aime2024/aime2024_llmjudge_gen_5e9f4f.py
opencompass/configs/datasets/aime2024/aime2024_llmverify_repeat16_gen_bf7475.py
opencompass/configs/datasets/aime2024/aime2024_llmverify_repeat8_gen_e8fcee.py
opencompass/configs/datasets/aime2025/aime2025_cascade_eval_gen_5e9f4f.py
opencompass/configs/datasets/aime2025/aime2025_llmjudge_academic.py
opencompass/configs/datasets/aime2025/aime2025_llmjudge_gen_5e9f4f.py
opencompass/configs/datasets/anli/anli_gen.py
opencompass/configs/datasets/anli/anli_gen_fc7328.py
opencompass/configs/datasets/anli/anli_ppl.py
opencompass/configs/datasets/anli/anli_ppl_1d290e.py
opencompass/configs/datasets/anthropics_evals/airisk_gen.py
opencompass/configs/datasets/anthropics_evals/airisk_gen_ba66fc.py
opencompass/configs/datasets/anthropics_evals/persona_gen.py
opencompass/configs/datasets/anthropics_evals/persona_gen_cc72e2.py
opencompass/configs/datasets/anthropics_evals/sycophancy_gen.py
opencompass/configs/datasets/anthropics_evals/sycophancy_gen_4bba45.py
opencompass/configs/datasets/apps/README.md
opencompass/configs/datasets/apps/apps_gen.py
opencompass/configs/datasets/apps/apps_gen_c7893a.py
opencompass/configs/datasets/apps/apps_mini_gen.py
opencompass/configs/datasets/apps/apps_mini_gen_c7893a.py
opencompass/configs/datasets/apps/deprecated_apps_gen_5b4254.py
opencompass/configs/datasets/apps/deprecated_apps_gen_7fbb95.py
opencompass/configs/datasets/apps/deprecated_apps_gen_b4dee3.py
opencompass/configs/datasets/babilong/README.md
opencompass/configs/datasets/babilong/babilong_0k_gen.py
opencompass/configs/datasets/babilong/babilong_128k_gen.py
opencompass/configs/datasets/babilong/babilong_16k_gen.py
opencompass/configs/datasets/babilong/babilong_1m_gen.py
opencompass/configs/datasets/babilong/babilong_256k_gen.py
opencompass/configs/datasets/babilong/babilong_2k_gen.py
opencompass/configs/datasets/babilong/babilong_32k_gen.py
opencompass/configs/datasets/babilong/babilong_4k_gen.py
opencompass/configs/datasets/bbeh/README.md
opencompass/configs/datasets/bbeh/bbeh_gen.py
opencompass/configs/datasets/bbeh/bbeh_llmjudge_gen_86c3a0.py
opencompass/configs/datasets/bbh/README.md
opencompass/configs/datasets/bbh/bbh_0shot_nocot_academic_gen.py
opencompass/configs/datasets/bbh/bbh_0shot_nocot_gen_925fc4.py
opencompass/configs/datasets/bbh/bbh_0shot_nocot_gen_9c32f6.py
opencompass/configs/datasets/bbh/bbh_0shot_nocot_gen_ea7952.py
opencompass/configs/datasets/bbh/bbh_gen.py
opencompass/configs/datasets/bbh/bbh_gen_2879b0.py
opencompass/configs/datasets/bbh/bbh_gen_4a31fa.py
opencompass/configs/datasets/bbh/bbh_gen_5b92b0.py
opencompass/configs/datasets/bbh/bbh_gen_5bf00b.py
opencompass/configs/datasets/bbh/bbh_gen_98fba6.py
opencompass/configs/datasets/bbh/bbh_gen_ee62e9.py
opencompass/configs/datasets/bbh/bbh_llm_judge_gen.py
opencompass/configs/datasets/bbh/bbh_llmjudge_gen_b5bdf1.py
opencompass/configs/datasets/bbh/bbh_subset_settings.py
opencompass/configs/datasets/bbh/lib_prompt/boolean_expressions.txt
opencompass/configs/datasets/bbh/lib_prompt/causal_judgement.txt
opencompass/configs/datasets/bbh/lib_prompt/date_understanding.txt
opencompass/configs/datasets/bbh/lib_prompt/disambiguation_qa.txt
opencompass/configs/datasets/bbh/lib_prompt/dyck_languages.txt
opencompass/configs/datasets/bbh/lib_prompt/formal_fallacies.txt
opencompass/configs/datasets/bbh/lib_prompt/geometric_shapes.txt
opencompass/configs/datasets/bbh/lib_prompt/hyperbaton.txt
opencompass/configs/datasets/bbh/lib_prompt/logical_deduction_five_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/logical_deduction_seven_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/logical_deduction_three_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/movie_recommendation.txt
opencompass/configs/datasets/bbh/lib_prompt/multistep_arithmetic_two.txt
opencompass/configs/datasets/bbh/lib_prompt/navigate.txt
opencompass/configs/datasets/bbh/lib_prompt/object_counting.txt
opencompass/configs/datasets/bbh/lib_prompt/penguins_in_a_table.txt
opencompass/configs/datasets/bbh/lib_prompt/reasoning_about_colored_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/ruin_names.txt
opencompass/configs/datasets/bbh/lib_prompt/salient_translation_error_detection.txt
opencompass/configs/datasets/bbh/lib_prompt/snarks.txt
opencompass/configs/datasets/bbh/lib_prompt/sports_understanding.txt
opencompass/configs/datasets/bbh/lib_prompt/temporal_sequences.txt
opencompass/configs/datasets/bbh/lib_prompt/tracking_shuffled_objects_five_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/tracking_shuffled_objects_seven_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/tracking_shuffled_objects_three_objects.txt
opencompass/configs/datasets/bbh/lib_prompt/web_of_lies.txt
opencompass/configs/datasets/bbh/lib_prompt/word_sorting.txt
opencompass/configs/datasets/bigcodebench/bigcodebench_full_complete_gen.py
opencompass/configs/datasets/bigcodebench/bigcodebench_full_complete_gen_faf748.py
opencompass/configs/datasets/bigcodebench/bigcodebench_full_instruct_gen.py
opencompass/configs/datasets/bigcodebench/bigcodebench_full_instruct_gen_8815eb.py
opencompass/configs/datasets/bigcodebench/bigcodebench_full_instruct_repeat_gen_c3d5ad.py
opencompass/configs/datasets/bigcodebench/bigcodebench_gen.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_complete_gen.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_complete_gen_2888d3.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_complete_gen_faf748.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen_8815eb.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_gen_c3d5ad.py
opencompass/configs/datasets/bigcodebench/bigcodebench_hard_instruct_repeat_gen_c3d5ad.py
opencompass/configs/datasets/calm/README.md
opencompass/configs/datasets/calm/calm.py
opencompass/configs/datasets/ceval/README.md
opencompass/configs/datasets/ceval/ceval_clean_ppl.py
opencompass/configs/datasets/ceval/ceval_gen.py
opencompass/configs/datasets/ceval/ceval_gen_2daf24.py
opencompass/configs/datasets/ceval/ceval_gen_5f30c7.py
opencompass/configs/datasets/ceval/ceval_internal_ppl_1cd8bf.py
opencompass/configs/datasets/ceval/ceval_internal_ppl_93e5ce.py
opencompass/configs/datasets/ceval/ceval_ppl.py
opencompass/configs/datasets/ceval/ceval_ppl_1cd8bf.py
opencompass/configs/datasets/ceval/ceval_ppl_578f8d.py
opencompass/configs/datasets/ceval/ceval_ppl_93e5ce.py
opencompass/configs/datasets/ceval/ceval_zero_shot_gen_bd40ef.py
opencompass/configs/datasets/chem_exam/competition_gen.py
opencompass/configs/datasets/chem_exam/gaokao_gen.py
opencompass/configs/datasets/chinese_simpleqa/README.md
opencompass/configs/datasets/chinese_simpleqa/chinese_simpleqa_gen.py
opencompass/configs/datasets/civilcomments/civilcomments_clp.py
opencompass/configs/datasets/civilcomments/civilcomments_clp_6a2561.py
opencompass/configs/datasets/civilcomments/civilcomments_clp_a3c5fd.py
opencompass/configs/datasets/clozeTest_maxmin/clozeTest_maxmin_gen.py
opencompass/configs/datasets/clozeTest_maxmin/clozeTest_maxmin_gen_c205fb.py
opencompass/configs/datasets/cmb/cmb_gen.py
opencompass/configs/datasets/cmb/cmb_gen_dfb5c4.py
opencompass/configs/datasets/cmmlu/cmmlu_0shot_cot_gen_305931.py
opencompass/configs/datasets/cmmlu/cmmlu_0shot_nocot_llmjudge_gen_e1cd9a.py
opencompass/configs/datasets/cmmlu/cmmlu_gen.py
opencompass/configs/datasets/cmmlu/cmmlu_gen_c13365.py
opencompass/configs/datasets/cmmlu/cmmlu_llm_judge_gen.py
opencompass/configs/datasets/cmmlu/cmmlu_llmjudge_gen_e1cd9a.py
opencompass/configs/datasets/cmmlu/cmmlu_ppl.py
opencompass/configs/datasets/cmmlu/cmmlu_ppl_041cbf.py
opencompass/configs/datasets/cmmlu/cmmlu_ppl_8b9c76.py
opencompass/configs/datasets/cmmlu/cmmlu_stem_0shot_nocot_gen_3653db.py
opencompass/configs/datasets/cmmlu/cmmlu_stem_0shot_nocot_llmjudge_gen_3653db.py
opencompass/configs/datasets/cmmlu/cmmlu_stem_0shot_nocot_xml_gen_3653db.py
opencompass/configs/datasets/cmo_fib/README.md
opencompass/configs/datasets/cmo_fib/cmo_fib_0shot_notcot_gen_4c6c29.py
opencompass/configs/datasets/cmo_fib/cmo_fib_gen.py
opencompass/configs/datasets/cmo_fib/cmo_fib_gen_2783e5.py
opencompass/configs/datasets/cmo_fib/cmo_fib_gen_ace24b.py
opencompass/configs/datasets/codecompass/codecompass_gen_079a6c.py
opencompass/configs/datasets/collections/base_core.py
opencompass/configs/datasets/collections/base_medium.py
opencompass/configs/datasets/collections/base_medium_llama.py
opencompass/configs/datasets/collections/base_small.py
opencompass/configs/datasets/collections/chat_core.py
opencompass/configs/datasets/collections/chat_medium.py
opencompass/configs/datasets/collections/chat_small.py
opencompass/configs/datasets/collections/example.py
opencompass/configs/datasets/collections/leaderboard/qwen.py
opencompass/configs/datasets/collections/leaderboard/qwen_chat.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_7shot_cot_gen_734a22.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_gen.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_gen_1da2d0.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_gen_c946f2.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl_3e9f2d.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl_5545e2.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl_716f78.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl_c49e77.py
opencompass/configs/datasets/commonsenseqa/commonsenseqa_ppl_e51e32.py
opencompass/configs/datasets/commonsenseqa_cn/commonsenseqacn_gen.py
opencompass/configs/datasets/commonsenseqa_cn/commonsenseqacn_gen_d380d0.py
opencompass/configs/datasets/commonsenseqa_cn/commonsenseqacn_ppl.py
opencompass/configs/datasets/commonsenseqa_cn/commonsenseqacn_ppl_971f48.py
opencompass/configs/datasets/compassbench_20_v1_1/agent/cibench_template_gen_e6b12a.py
opencompass/configs/datasets/compassbench_20_v1_1/agent/mus_teval_gen_105c48.py
opencompass/configs/datasets/compassbench_20_v1_1/code/compassbench_v1_1_code_gen_986f01.py
opencompass/configs/datasets/compassbench_20_v1_1/knowledge/compassbench_v1_knowledge_gen_bd74e0.py
opencompass/configs/datasets/compassbench_20_v1_1/language/compassbench_v1_language_gen_7aa06d.py
opencompass/configs/datasets/compassbench_20_v1_1/math/compassbench_v1_1_math_gen_1dc21d.py
opencompass/configs/datasets/compassbench_20_v1_1/math/mathbench_prompt.py
opencompass/configs/datasets/compassbench_20_v1_1/reason/compassbench_v1_reason_gen_d26d08.py
opencompass/configs/datasets/compassbench_20_v1_1_public/agent/cibench_template_gen_e6b12a.py
opencompass/configs/datasets/compassbench_20_v1_1_public/agent/mus_teval_gen_105c48.py
opencompass/configs/datasets/compassbench_20_v1_1_public/code/compassbench_v1_1_code_gen_986f01.py
opencompass/configs/datasets/compassbench_20_v1_1_public/knowledge/compassbench_v1_knowledge_gen_bd74e0.py
opencompass/configs/datasets/compassbench_20_v1_1_public/language/compassbench_v1_language_gen_7aa06d.py
opencompass/configs/datasets/compassbench_20_v1_1_public/math/compassbench_v1_1_math_gen_1dc21d.py
opencompass/configs/datasets/compassbench_20_v1_1_public/math/mathbench_prompt.py
opencompass/configs/datasets/compassbench_20_v1_1_public/reason/compassbench_v1_reason_gen_d26d08.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_code_gen_c8c3aa.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_knowledge.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_math.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_objective_gen.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_objective_gen_068af0.py
opencompass/configs/datasets/compassbench_v1_3/compassbench_v1_3_prompt.py
opencompass/configs/datasets/contamination/ceval_contamination_ppl_810ec6.py
opencompass/configs/datasets/contamination/mbpp_contamination_ppl_f01cb6.py
opencompass/configs/datasets/contamination/mmlu_contamination_ppl_810ec6.py
opencompass/configs/datasets/crowspairs/crowspairs_gen.py
opencompass/configs/datasets/crowspairs/crowspairs_gen_02b6c1.py
opencompass/configs/datasets/crowspairs/crowspairs_gen_381af0.py
opencompass/configs/datasets/crowspairs/crowspairs_ppl.py
opencompass/configs/datasets/crowspairs/crowspairs_ppl_47f211.py
opencompass/configs/datasets/crowspairs/crowspairs_ppl_e811e1.py
opencompass/configs/datasets/crowspairs_cn/crowspairscn_gen.py
opencompass/configs/datasets/crowspairs_cn/crowspairscn_gen_556dc9.py
opencompass/configs/datasets/crowspairs_cn/crowspairscn_ppl.py
opencompass/configs/datasets/crowspairs_cn/crowspairscn_ppl_f53575.py
opencompass/configs/datasets/cvalues/cvalues_responsibility_gen.py
opencompass/configs/datasets/cvalues/cvalues_responsibility_gen_543378.py
opencompass/configs/datasets/demo/demo_cmmlu_base_ppl.py
opencompass/configs/datasets/demo/demo_cmmlu_chat_gen.py
opencompass/configs/datasets/demo/demo_gsm8k_base_gen.py
opencompass/configs/datasets/demo/demo_gsm8k_chat_gen.py
opencompass/configs/datasets/demo/demo_math_base_gen.py
opencompass/configs/datasets/demo/demo_math_chat_gen.py
opencompass/configs/datasets/dingo/dingo_gen.py
opencompass/configs/datasets/drop/deprecated_drop_gen_8a9ed9.py
opencompass/configs/datasets/drop/drop_examples.py
opencompass/configs/datasets/drop/drop_gen.py
opencompass/configs/datasets/drop/drop_gen_a2697c.py
opencompass/configs/datasets/drop/drop_gen_eb14af.py
opencompass/configs/datasets/drop/drop_llm_judge_gen.py
opencompass/configs/datasets/drop/drop_llmjudge_gen_3857b0.py
opencompass/configs/datasets/drop/drop_openai_simple_evals_gen_3857b0.py
opencompass/configs/datasets/ds1000/ds1000_compl_gen_cbc84f.py
opencompass/configs/datasets/ds1000/ds1000_compl_service_eval_gen_cbc84f.py
opencompass/configs/datasets/ds1000/ds1000_gen_5c4bec.py
opencompass/configs/datasets/ds1000/ds1000_gen_cbc84f.py
opencompass/configs/datasets/ds1000/ds1000_service_eval_gen_cbc84f.py
opencompass/configs/datasets/eese/eese_llm_judge_gen.py
opencompass/configs/datasets/flores/flores_gen.py
opencompass/configs/datasets/flores/flores_gen_806ede.py
opencompass/configs/datasets/flores/flores_gen_aad4fd.py
opencompass/configs/datasets/game24/game24_gen.py
opencompass/configs/datasets/game24/game24_gen_52a460.py
opencompass/configs/datasets/gaokao_math/README.md
opencompass/configs/datasets/gaokao_math/gaokao_math_gen_f5fd28.py
opencompass/configs/datasets/govrepcrs/govrepcrs_gen.py
opencompass/configs/datasets/govrepcrs/govrepcrs_gen_aa5eb3.py
opencompass/configs/datasets/govrepcrs/govrepcrs_gen_db7930.py
opencompass/configs/datasets/gpqa/README.md
opencompass/configs/datasets/gpqa/gpqa_0shot_nocot_gen_772ea0.py
opencompass/configs/datasets/gpqa/gpqa_0shot_nocot_genericllmeval_gen_772ea0.py
opencompass/configs/datasets/gpqa/gpqa_0shot_nocot_genericllmeval_xml_gen_772ea0.py
opencompass/configs/datasets/gpqa/gpqa_0shot_nocot_llmjudge_gen_772ea0.py
opencompass/configs/datasets/gpqa/gpqa_cascade_eval_academic.py
opencompass/configs/datasets/gpqa/gpqa_cascade_eval_gen_772ea0.py
opencompass/configs/datasets/gpqa/gpqa_few_shot_ppl_4b5a83.py
opencompass/configs/datasets/gpqa/gpqa_gen.py
opencompass/configs/datasets/gpqa/gpqa_gen_015262.py
opencompass/configs/datasets/gpqa/gpqa_gen_4baadb.py
opencompass/configs/datasets/gpqa/gpqa_llm_judge_gen.py
opencompass/configs/datasets/gpqa/gpqa_openai_simple_evals_gen_5aeece.py
opencompass/configs/datasets/gpqa/gpqa_ppl_6bf57a.py
opencompass/configs/datasets/gsm8k/README.md
opencompass/configs/datasets/gsm8k/deprecated_gsm8k_agent_gen_be1606.py
opencompass/configs/datasets/gsm8k/gsm8k_0shot_gen_a58960.py
opencompass/configs/datasets/gsm8k/gsm8k_0shot_nocot_gen_6cbf22.py
opencompass/configs/datasets/gsm8k/gsm8k_0shot_v2_gen_17d799.py
opencompass/configs/datasets/gsm8k/gsm8k_0shot_v2_gen_6e39a4.py
opencompass/configs/datasets/gsm8k/gsm8k_0shot_v2_gen_a58960.py
opencompass/configs/datasets/gsm8k/gsm8k_agent_gen_c3dff3.py
opencompass/configs/datasets/gsm8k/gsm8k_gen.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_17d0dc.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_1d7fe4.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_1dce88.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_3309bd.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_57b0b1.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_701491.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_a3e34a.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_d6de81.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_e9e91e.py
opencompass/configs/datasets/gsm8k/gsm8k_gen_ee684f.py
opencompass/configs/datasets/gsm8k/gsm8k_model_postprocess_gen_a58960.py
opencompass/configs/datasets/gsm8k/gsm8k_xfinder_gen_a58960.py
opencompass/configs/datasets/gsm8k_contamination/gsm8k_contamination_ppl_ecdd22.py
opencompass/configs/datasets/gsm_hard/gsmhard_gen.py
opencompass/configs/datasets/gsm_hard/gsmhard_gen_8a1400.py
opencompass/configs/datasets/hellaswag/README.md
opencompass/configs/datasets/hellaswag/hellaswag_10shot_gen_e42710.py
opencompass/configs/datasets/hellaswag/hellaswag_10shot_ppl_59c85e.py
opencompass/configs/datasets/hellaswag/hellaswag_clean_ppl.py
opencompass/configs/datasets/hellaswag/hellaswag_gen.py
opencompass/configs/datasets/hellaswag/hellaswag_gen_6faab5.py
opencompass/configs/datasets/hellaswag/hellaswag_llm_judge_gen.py
opencompass/configs/datasets/hellaswag/hellaswag_llmjudge_gen_809ef1.py
opencompass/configs/datasets/hellaswag/hellaswag_ppl.py
opencompass/configs/datasets/hellaswag/hellaswag_ppl_47bff9.py
opencompass/configs/datasets/hellaswag/hellaswag_ppl_7d7f2d.py
opencompass/configs/datasets/hellaswag/hellaswag_ppl_9dbb12.py
opencompass/configs/datasets/hellaswag/hellaswag_ppl_a6e128.py
opencompass/configs/datasets/humaneval/README.md
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_4a6eef.py
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_6d1cc2.py
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_a82cae.py
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_d2537e.py
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_fd5822.py
opencompass/configs/datasets/humaneval/deprecated_humaneval_gen_ff7054.py
opencompass/configs/datasets/humaneval/humaneval_gen.py
opencompass/configs/datasets/humaneval/humaneval_gen_66a7f4.py
opencompass/configs/datasets/humaneval/humaneval_gen_8e312c.py
opencompass/configs/datasets/humaneval/humaneval_openai_sample_evals_gen_159614.py
opencompass/configs/datasets/humaneval/humaneval_openai_sample_evals_gen_dcae0e.py
opencompass/configs/datasets/humaneval/humaneval_openai_sample_evals_o1_gen_5e7b00.py
opencompass/configs/datasets/humaneval/humaneval_openai_sample_evals_repeat_gen_dcae0e.py
opencompass/configs/datasets/humaneval/humaneval_passk_gen_8e312c.py
opencompass/configs/datasets/humaneval/humaneval_repeat10_gen_8e312c.py
opencompass/configs/datasets/humaneval/internal_humaneval_gen_ce6b06.py
opencompass/configs/datasets/humaneval/internal_humaneval_gen_d2537e.py
opencompass/configs/datasets/humaneval_cn/humaneval_cn_gen.py
opencompass/configs/datasets/humaneval_cn/humaneval_cn_gen_6313aa.py
opencompass/configs/datasets/humaneval_cn/humaneval_cn_passk_gen_6313aa.py
opencompass/configs/datasets/humaneval_cn/humaneval_cn_repeat10_gen_6313aa.py
opencompass/configs/datasets/humaneval_multi/humaneval_multi_gen.py
opencompass/configs/datasets/humaneval_multi/humaneval_multi_gen_82cf85.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_gen.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_gen_66a7f4.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_gen_8e312c.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_openai_simple_evals_gen_159614.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_passk_gen_8e312c.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_repeat10_gen_8e312c.py
opencompass/configs/datasets/humaneval_plus/humaneval_plus_repeat_gen_41b01c.py
opencompass/configs/datasets/humaneval_pro/README.md
opencompass/configs/datasets/humaneval_pro/humaneval_pro_gen.py
opencompass/configs/datasets/humaneval_pro/humaneval_pro_gen_3dc067.py
opencompass/configs/datasets/humaneval_pro/humaneval_pro_repeat_gen_3dc067.py
opencompass/configs/datasets/humanevalx/humanevalx_0shot_nocot_gen_3e4bbd.py
opencompass/configs/datasets/humanevalx/humanevalx_gen.py
opencompass/configs/datasets/humanevalx/humanevalx_gen_0af626.py
opencompass/configs/datasets/humanevalx/humanevalx_gen_3d84a3.py
opencompass/configs/datasets/humanevalx/humanevalx_gen_620cfa.py
opencompass/configs/datasets/humanevalx/humanevalx_repeat_gen_3d84a3.py
opencompass/configs/datasets/hungarian_exam/hungarian_exam_gen.py
opencompass/configs/datasets/hungarian_exam/hungarian_exam_gen_8a1435.py
opencompass/configs/datasets/inference_ppl/README.md
opencompass/configs/datasets/inference_ppl/inference_ppl.py
opencompass/configs/datasets/infinitebench/infinitebench.py
opencompass/configs/datasets/infinitebench/infinitebenchcodedebug/infinitebench_codedebug_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchcodedebug/infinitebench_codedebug_gen_276a42.py
opencompass/configs/datasets/infinitebench/infinitebenchcoderun/infinitebench_coderun_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchcoderun/infinitebench_coderun_gen_1a76bd.py
opencompass/configs/datasets/infinitebench/infinitebenchendia/infinitebench_endia_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchendia/infinitebench_endia_gen_c96eb5.py
opencompass/configs/datasets/infinitebench/infinitebenchenmc/infinitebench_enmc_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchenmc/infinitebench_enmc_gen_3a4102.py
opencompass/configs/datasets/infinitebench/infinitebenchenqa/infinitebench_enqa_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchenqa/infinitebench_enqa_gen_a1640c.py
opencompass/configs/datasets/infinitebench/infinitebenchensum/infinitebench_ensum_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchensum/infinitebench_ensum_gen_cfbc08.py
opencompass/configs/datasets/infinitebench/infinitebenchmathcalc/infinitebench_mathcalc_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchmathcalc/infinitebench_mathcalc_gen_78d17e.py
opencompass/configs/datasets/infinitebench/infinitebenchmathfind/infinitebench_mathfind_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchmathfind/infinitebench_mathfind_gen_6d799e.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievekv/infinitebench_retrievekv_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievekv/infinitebench_retrievekv_gen_06b3ac.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievenumber/infinitebench_retrievenumber_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievenumber/infinitebench_retrievenumber_gen_047436.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievepasskey/infinitebench_retrievepasskey_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchretrievepasskey/infinitebench_retrievepasskey_gen_62ff68.py
opencompass/configs/datasets/infinitebench/infinitebenchzhqa/infinitebench_zhqa_gen.py
opencompass/configs/datasets/infinitebench/infinitebenchzhqa/infinitebench_zhqa_gen_1e5293.py
opencompass/configs/datasets/internsandbox/internsandbox_gen.py
opencompass/configs/datasets/internsandbox/internsandbox_gen_44b982.py
opencompass/configs/datasets/iwslt2017/iwslt2017_gen.py
opencompass/configs/datasets/iwslt2017/iwslt2017_gen_69ce16.py
opencompass/configs/datasets/iwslt2017/iwslt2017_gen_b4a814.py
opencompass/configs/datasets/iwslt2017/iwslt2017_gen_d0ebd1.py
opencompass/configs/datasets/jigsawmultilingual/jigsawmultilingual_clp.py
opencompass/configs/datasets/jigsawmultilingual/jigsawmultilingual_clp_1af0ae.py
opencompass/configs/datasets/jigsawmultilingual/jigsawmultilingual_clp_fe50d8.py
opencompass/configs/datasets/judge/judgebench.py
opencompass/configs/datasets/judge/judgerbenchv2.py
opencompass/configs/datasets/judge/rewardbench.py
opencompass/configs/datasets/judge/rmb.py
opencompass/configs/datasets/kaoshi/kaoshi_gen.py
opencompass/configs/datasets/kaoshi/kaoshi_gen_86aca2.py
opencompass/configs/datasets/kcle/kcle_llm_judge_gen.py
opencompass/configs/datasets/korbench/korbench_gen.py
opencompass/configs/datasets/korbench/korbench_llm_judge_gen.py
opencompass/configs/datasets/korbench/korbench_llmjudge_gen_17854d.py
opencompass/configs/datasets/korbench/korbench_llmjudge_gen_56cf43.py
opencompass/configs/datasets/korbench/korbench_mixed_gen_d00bdd.py
opencompass/configs/datasets/korbench/korbench_single_0_shot_gen.py
opencompass/configs/datasets/korbench/korbench_single_0shot_cascade_eval_gen_56cf43.py
opencompass/configs/datasets/korbench/korbench_single_0shot_genericllmeval_gen_17854d.py
opencompass/configs/datasets/korbench/korbench_single_0shot_llmjudge_gen.py
opencompass/configs/datasets/korbench/korbench_single_3_shot_gen.py
opencompass/configs/datasets/korbench/readme.md
opencompass/configs/datasets/lambada/lambada_gen.py
opencompass/configs/datasets/lambada/lambada_gen_217e11.py
opencompass/configs/datasets/lambada/lambada_gen_8b48a5.py
opencompass/configs/datasets/lawbench/lawbench_one_shot_gen_002588.py
opencompass/configs/datasets/lawbench/lawbench_zero_shot_gen_002588.py
opencompass/configs/datasets/lcsts/lcsts_gen.py
opencompass/configs/datasets/lcsts/lcsts_gen_8ee1fe.py
opencompass/configs/datasets/lcsts/lcsts_gen_9b0b89.py
opencompass/configs/datasets/leval/leval.py
opencompass/configs/datasets/leval/levalcoursera/leval_coursera_gen.py
opencompass/configs/datasets/leval/levalcoursera/leval_coursera_gen_36a006.py
opencompass/configs/datasets/leval/levalfinancialqa/leval_financialqa_gen.py
opencompass/configs/datasets/leval/levalfinancialqa/leval_financialqa_gen_b03798.py
opencompass/configs/datasets/leval/levalgovreportsumm/leval_gov_report_summ_gen.py
opencompass/configs/datasets/leval/levalgovreportsumm/leval_gov_report_summ_gen_b03798.py
opencompass/configs/datasets/leval/levalgsm100/leval_gsm100_gen.py
opencompass/configs/datasets/leval/levalgsm100/leval_gsm100_gen_77dd94.py
opencompass/configs/datasets/leval/levallegalcontractqa/leval_legalcontractqa_gen.py
opencompass/configs/datasets/leval/levallegalcontractqa/leval_legalcontractqa_gen_68a2ac.py
opencompass/configs/datasets/leval/levalmeetingsumm/leval_meetingsumm_gen.py
opencompass/configs/datasets/leval/levalmeetingsumm/leval_meetingsumm_gen_b03798.py
opencompass/configs/datasets/leval/levalmultidocqa/leval_multidocqa_gen.py
opencompass/configs/datasets/leval/levalmultidocqa/leval_multidocqa_gen_96bf3f.py
opencompass/configs/datasets/leval/levalnarrativeqa/leval_narrativeqa_gen.py
opencompass/configs/datasets/leval/levalnarrativeqa/leval_narrativeqa_gen_766dd0.py
opencompass/configs/datasets/leval/levalnaturalquestion/leval_naturalquestion_gen.py
opencompass/configs/datasets/leval/levalnaturalquestion/leval_naturalquestion_gen_52c33f.py
opencompass/configs/datasets/leval/levalnewssumm/leval_newssumm_gen.py
opencompass/configs/datasets/leval/levalnewssumm/leval_newssumm_gen_b03798.py
opencompass/configs/datasets/leval/levalpaperassistant/leval_paper_assistant_gen.py
opencompass/configs/datasets/leval/levalpaperassistant/leval_paper_assistant_gen_b03798.py
opencompass/configs/datasets/leval/levalpatentsumm/leval_patent_summ_gen.py
opencompass/configs/datasets/leval/levalpatentsumm/leval_patent_summ_gen_b03798.py
opencompass/configs/datasets/leval/levalquality/leval_quality_gen.py
opencompass/configs/datasets/leval/levalquality/leval_quality_gen_36a006.py
opencompass/configs/datasets/leval/levalreviewsumm/leval_review_summ_gen.py
opencompass/configs/datasets/leval/levalreviewsumm/leval_review_summ_gen_b03798.py
opencompass/configs/datasets/leval/levalscientificqa/leval_scientificqa_gen.py
opencompass/configs/datasets/leval/levalscientificqa/leval_scientificqa_gen_96bf3f.py
opencompass/configs/datasets/leval/levaltopicretrieval/leval_topic_retrieval_gen.py
opencompass/configs/datasets/leval/levaltopicretrieval/leval_topic_retrieval_gen_bf433f.py
opencompass/configs/datasets/leval/levaltpo/leval_tpo_gen.py
opencompass/configs/datasets/leval/levaltpo/leval_tpo_gen_36a006.py
opencompass/configs/datasets/leval/levaltvshowsumm/leval_tvshow_summ_gen.py
opencompass/configs/datasets/leval/levaltvshowsumm/leval_tvshow_summ_gen_b03798.py
opencompass/configs/datasets/livecodebench/README.md
opencompass/configs/datasets/livecodebench/livecodebench_code_generation_repeat_gen_b5b6c5.py
opencompass/configs/datasets/livecodebench/livecodebench_gen.py
opencompass/configs/datasets/livecodebench/livecodebench_gen_6966bc.py
opencompass/configs/datasets/livecodebench/livecodebench_gen_a4f90b.py
opencompass/configs/datasets/livecodebench/livecodebench_gen_b2b0fd.py
opencompass/configs/datasets/livecodebench/livecodebench_o1_gen_f0ed6c.py
opencompass/configs/datasets/livecodebench/livecodebench_split_v4_o1_gen_f0ed6c.py
opencompass/configs/datasets/livecodebench/livecodebench_split_v4_o1_postprocess_gen_f0ed6c.py
opencompass/configs/datasets/livecodebench/livecodebench_time_split_gen_a4f90b.py
opencompass/configs/datasets/livecodebench/livecodebench_v1_o1_gen_f0ed6c.py
opencompass/configs/datasets/livecodebench/livecodebench_v6_academic.py
opencompass/configs/datasets/livemathbench/README.md
opencompass/configs/datasets/livemathbench/livemathbench_gen.py
opencompass/configs/datasets/livemathbench/livemathbench_gen_6eb711.py
opencompass/configs/datasets/livemathbench/livemathbench_gen_9befbf.py
opencompass/configs/datasets/livemathbench/livemathbench_gen_caed8f.py
opencompass/configs/datasets/livemathbench/livemathbench_greedy_gen.py
opencompass/configs/datasets/livemathbench/livemathbench_greedy_gen_9befbf.py
opencompass/configs/datasets/livemathbench/livemathbench_hard_custom_cascade_eval_gen_4bce59.py
opencompass/configs/datasets/livemathbench/livemathbench_hard_custom_llmverify_gen_85d0ef.py
opencompass/configs/datasets/livemathbench/livemathbench_hard_gen_353ae7.py
opencompass/configs/datasets/livemathbench/livemathbench_hard_greedy_gen_353ae7.py
opencompass/configs/datasets/livemathbench/livemathbench_hard_llmjudge_gen_71eaf5.py
opencompass/configs/datasets/livemathbench/livemathbench_v202505_gen_9befbf.py
opencompass/configs/datasets/livemathbench/livemathbench_v202505_greedy_gen_9befbf.py
opencompass/configs/datasets/livemathbench/livemathbench_v202505_hard_gen_353ae7.py
opencompass/configs/datasets/livemathbench/livemathbench_v202505_hard_greedy_gen_353ae7.py
opencompass/configs/datasets/livereasonbench/livereasonbench_gen.py
opencompass/configs/datasets/livereasonbench/livereasonbench_gen_f990de.py
opencompass/configs/datasets/livereasonbench/livereasonbench_genericllmeval_gen_f990de.py
opencompass/configs/datasets/livereasonbench/livereasonbench_llmverify_20250428_gen_0484cb.py
opencompass/configs/datasets/livestembench/livestembench_0shot_noncot_gen_2e6d10.py
opencompass/configs/datasets/livestembench/livestembench_0shot_noncot_xml_gen_2e6d10.py
opencompass/configs/datasets/livestembench/livestembench_gen.py
opencompass/configs/datasets/livestembench/livestembench_gen_3e3c50.py
opencompass/configs/datasets/llm_compression/README.md
opencompass/configs/datasets/llm_compression/llm_compression.py
opencompass/configs/datasets/longbench/longbench.py
opencompass/configs/datasets/longbench/longbench2wikimqa/longbench_2wikimqa_gen.py
opencompass/configs/datasets/longbench/longbench2wikimqa/longbench_2wikimqa_gen_6b3efc.py
opencompass/configs/datasets/longbench/longbenchdureader/longbench_dureader_gen.py
opencompass/configs/datasets/longbench/longbenchdureader/longbench_dureader_gen_c6c7e4.py
opencompass/configs/datasets/longbench/longbenchgov_report/longbench_gov_report_gen.py
opencompass/configs/datasets/longbench/longbenchgov_report/longbench_gov_report_gen_54c5b0.py
opencompass/configs/datasets/longbench/longbenchhotpotqa/longbench_hotpotqa_gen.py
opencompass/configs/datasets/longbench/longbenchhotpotqa/longbench_hotpotqa_gen_6b3efc.py
opencompass/configs/datasets/longbench/longbenchlcc/longbench_lcc_gen.py
opencompass/configs/datasets/longbench/longbenchlcc/longbench_lcc_gen_6ba507.py
opencompass/configs/datasets/longbench/longbenchlsht/longbench_lsht_gen.py
opencompass/configs/datasets/longbench/longbenchlsht/longbench_lsht_gen_e8a339.py
opencompass/configs/datasets/longbench/longbenchmulti_news/longbench_multi_news_gen.py
opencompass/configs/datasets/longbench/longbenchmulti_news/longbench_multi_news_gen_6f9da9.py
opencompass/configs/datasets/longbench/longbenchmultifieldqa_en/longbench_multifieldqa_en_gen.py
opencompass/configs/datasets/longbench/longbenchmultifieldqa_en/longbench_multifieldqa_en_gen_d3838e.py
opencompass/configs/datasets/longbench/longbenchmultifieldqa_zh/longbench_multifieldqa_zh_gen.py
opencompass/configs/datasets/longbench/longbenchmultifieldqa_zh/longbench_multifieldqa_zh_gen_e9a7ef.py
opencompass/configs/datasets/longbench/longbenchmusique/longbench_musique_gen.py
opencompass/configs/datasets/longbench/longbenchmusique/longbench_musique_gen_6b3efc.py
opencompass/configs/datasets/longbench/longbenchnarrativeqa/longbench_narrativeqa_gen.py
opencompass/configs/datasets/longbench/longbenchnarrativeqa/longbench_narrativeqa_gen_a68305.py
opencompass/configs/datasets/longbench/longbenchpassage_count/longbench_passage_count_gen.py
opencompass/configs/datasets/longbench/longbenchpassage_count/longbench_passage_count_gen_dcdaab.py
opencompass/configs/datasets/longbench/longbenchpassage_retrieval_en/longbench_passage_retrieval_en_gen.py
opencompass/configs/datasets/longbench/longbenchpassage_retrieval_en/longbench_passage_retrieval_en_gen_734db5.py
opencompass/configs/datasets/longbench/longbenchpassage_retrieval_zh/longbench_passage_retrieval_zh_gen.py
opencompass/configs/datasets/longbench/longbenchpassage_retrieval_zh/longbench_passage_retrieval_zh_gen_01cca2.py
opencompass/configs/datasets/longbench/longbenchqasper/longbench_qasper_gen.py
opencompass/configs/datasets/longbench/longbenchqasper/longbench_qasper_gen_6b3efc.py
opencompass/configs/datasets/longbench/longbenchqmsum/longbench_qmsum_gen.py
opencompass/configs/datasets/longbench/longbenchqmsum/longbench_qmsum_gen_d33331.py
opencompass/configs/datasets/longbench/longbenchrepobench/longbench_repobench_gen.py
opencompass/configs/datasets/longbench/longbenchrepobench/longbench_repobench_gen_6df953.py
opencompass/configs/datasets/longbench/longbenchsamsum/longbench_samsum_gen.py
opencompass/configs/datasets/longbench/longbenchsamsum/longbench_samsum_gen_f4416d.py
opencompass/configs/datasets/longbench/longbenchtrec/longbench_trec_gen.py
opencompass/configs/datasets/longbench/longbenchtrec/longbench_trec_gen_824187.py
opencompass/configs/datasets/longbench/longbenchtriviaqa/longbench_triviaqa_gen.py
opencompass/configs/datasets/longbench/longbenchtriviaqa/longbench_triviaqa_gen_d30cb9.py
opencompass/configs/datasets/longbench/longbenchvcsum/longbench_vcsum_gen.py
opencompass/configs/datasets/longbench/longbenchvcsum/longbench_vcsum_gen_f7a8ac.py
opencompass/configs/datasets/longbenchv2/longbenchv2_gen.py
opencompass/configs/datasets/longbenchv2/longbenchv2_gen_75fbba.py
opencompass/configs/datasets/lveval/lveval.md
opencompass/configs/datasets/lveval/lveval.py
opencompass/configs/datasets/lveval/lvevalcmrc_mixup/lveval_cmrc_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalcmrc_mixup/lveval_cmrc_mixup_gen_465823.py
opencompass/configs/datasets/lveval/lvevaldureader_mixup/lveval_dureader_mixup_gen.py
opencompass/configs/datasets/lveval/lvevaldureader_mixup/lveval_dureader_mixup_gen_465823.py
opencompass/configs/datasets/lveval/lvevalfactrecall_en/lveval_factrecall_en_gen.py
opencompass/configs/datasets/lveval/lvevalfactrecall_en/lveval_factrecall_en_gen_9a836f.py
opencompass/configs/datasets/lveval/lvevalfactrecall_zh/lveval_factrecall_zh_gen.py
opencompass/configs/datasets/lveval/lvevalfactrecall_zh/lveval_factrecall_zh_gen_dbee70.py
opencompass/configs/datasets/lveval/lvevalhotpotwikiqa_mixup/lveval_hotpotwikiqa_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalhotpotwikiqa_mixup/lveval_hotpotwikiqa_mixup_gen_77ce82.py
opencompass/configs/datasets/lveval/lvevallic_mixup/lveval_lic_mixup_gen.py
opencompass/configs/datasets/lveval/lvevallic_mixup/lveval_lic_mixup_gen_01eb0c.py
opencompass/configs/datasets/lveval/lvevalloogle_CR_mixup/lveval_loogle_CR_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalloogle_CR_mixup/lveval_loogle_CR_mixup_gen_d7ea36.py
opencompass/configs/datasets/lveval/lvevalloogle_MIR_mixup/lveval_loogle_MIR_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalloogle_MIR_mixup/lveval_loogle_MIR_mixup_gen_d7ea36.py
opencompass/configs/datasets/lveval/lvevalloogle_SD_mixup/lveval_loogle_SD_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalloogle_SD_mixup/lveval_loogle_SD_mixup_gen_d7ea36.py
opencompass/configs/datasets/lveval/lvevalmultifieldqa_en_mixup/lveval_multifieldqa_en_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalmultifieldqa_en_mixup/lveval_multifieldqa_en_mixup_gen_d7ea36.py
opencompass/configs/datasets/lveval/lvevalmultifieldqa_zh_mixup/lveval_multifieldqa_zh_mixup_gen.py
opencompass/configs/datasets/lveval/lvevalmultifieldqa_zh_mixup/lveval_multifieldqa_zh_mixup_gen_0fbdad.py
opencompass/configs/datasets/mastermath2024v1/mastermath2024v1_gen.py
opencompass/configs/datasets/mastermath2024v1/mastermath2024v1_gen_be6318.py
opencompass/configs/datasets/matbench/matbench_gen.py
opencompass/configs/datasets/matbench/matbench_gen_f71840.py
opencompass/configs/datasets/matbench/matbench_llm_judge_gen_0e9276.py
opencompass/configs/datasets/matbench/matbench_regex_judge_gen_0e9276.py
opencompass/configs/datasets/math/README.md
opencompass/configs/datasets/math/deprecated_math_agent_evaluatorv2_gen_861b4f.py
opencompass/configs/datasets/math/deprecated_math_evaluatorv2_gen_265cce.py
opencompass/configs/datasets/math/math_0shot_gen_11c4b5.py
opencompass/configs/datasets/math/math_0shot_gen_393424.py
opencompass/configs/datasets/math/math_0shot_llm_judge_gen_393424.py
opencompass/configs/datasets/math/math_0shot_llm_judge_v2_gen_31d777.py
opencompass/configs/datasets/math/math_4shot_base_gen_43d5b6.py
opencompass/configs/datasets/math/math_4shot_base_gen_db136b.py
opencompass/configs/datasets/math/math_4shot_example_from_google_research.py
opencompass/configs/datasets/math/math_500_cascade_eval_gen_6ff468.py
opencompass/configs/datasets/math/math_500_gen.py
opencompass/configs/datasets/math/math_500_llmjudge_gen_6ff468.py
opencompass/configs/datasets/math/math_agent_evaluatorv2_gen_0c1b4e.py
opencompass/configs/datasets/math/math_agent_gen_0c1b4e.py
opencompass/configs/datasets/math/math_agent_gen_861b4f.py
opencompass/configs/datasets/math/math_agent_gen_af2293.py
opencompass/configs/datasets/math/math_evaluatorv2_gen_2f4a71.py
opencompass/configs/datasets/math/math_evaluatorv2_gen_cecb31.py
opencompass/configs/datasets/math/math_gen.py
opencompass/configs/datasets/math/math_gen_0957ff.py
opencompass/configs/datasets/math/math_gen_1ed9c2.py
opencompass/configs/datasets/math/math_gen_265cce.py
opencompass/configs/datasets/math/math_gen_559593.py
opencompass/configs/datasets/math/math_gen_5e8458.py
opencompass/configs/datasets/math/math_gen_736506.py
opencompass/configs/datasets/math/math_gen_78ced2.py
opencompass/configs/datasets/math/math_gen_943d32.py
opencompass/configs/datasets/math/math_gen_a58d9d.py
opencompass/configs/datasets/math/math_intern_evaluator_gen_265cce.py
opencompass/configs/datasets/math/math_llm_judge_gen.py
opencompass/configs/datasets/math/math_llm_judge_gen_56606f.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_academic_gen.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_gen.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_cot_gen_11c4b5.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_gen_b27274.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_genericllmeval_gen_63a000.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_genericllmeval_gen_6ff468.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_genericllmeval_xml_gen_63a000.py
opencompass/configs/datasets/math/math_prm800k_500_0shot_nocot_llmjudge_gen_63a000.py
opencompass/configs/datasets/math/math_prm800k_500_gen.py
opencompass/configs/datasets/math/math_prm800k_500_gen_393424.py
opencompass/configs/datasets/math/math_prm800k_500_llm_judge_gen.py
opencompass/configs/datasets/math/math_prm800k_500_llmverify_gen_6ff468.py
opencompass/configs/datasets/math/math_prm800k_500_llmverify_repeat4_gen_97b203.py
opencompass/configs/datasets/math401/math401_gen.py
opencompass/configs/datasets/math401/math401_gen_ab5f39.py
opencompass/configs/datasets/mbpp/README.md
opencompass/configs/datasets/mbpp/deprecated_mbpp_gen_1e1056.py
opencompass/configs/datasets/mbpp/deprecated_mbpp_gen_6590b0.py
opencompass/configs/datasets/mbpp/deprecated_mbpp_gen_caa7ab.py
opencompass/configs/datasets/mbpp/deprecated_mbpp_passk_gen_1e1056.py
opencompass/configs/datasets/mbpp/deprecated_mbpp_repeat10_gen_1e1056.py
opencompass/configs/datasets/mbpp/deprecated_sanitized_mbpp_gen_1e1056.py
opencompass/configs/datasets/mbpp/deprecated_sanitized_mbpp_gen_cb43ef.py
opencompass/configs/datasets/mbpp/deprecated_sanitized_mbpp_passk_gen_1e1056.py
opencompass/configs/datasets/mbpp/deprecated_sanitized_mbpp_repeat10_gen_1e1056.py
opencompass/configs/datasets/mbpp/mbpp_gen.py
opencompass/configs/datasets/mbpp/mbpp_gen_830460.py
opencompass/configs/datasets/mbpp/mbpp_passk_gen_830460.py
opencompass/configs/datasets/mbpp/mbpp_repeat10_gen_830460.py
opencompass/configs/datasets/mbpp/mbpp_repeat_gen_18dd1b.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_gen_742f0c.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_gen_830460.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_gen_a0fc46.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_mdblock_0shot_nocot_gen_a2e416.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_mdblock_gen_a447ff.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_passk_gen_830460.py
opencompass/configs/datasets/mbpp/sanitized_mbpp_repeat10_gen_830460.py
opencompass/configs/datasets/mbpp_cn/deprecated_mbpp_cn_gen_1d1481.py
opencompass/configs/datasets/mbpp_cn/deprecated_mbpp_cn_passk_gen_1d1481.py
opencompass/configs/datasets/mbpp_cn/deprecated_mbpp_cn_repeat10_gen_1d1481.py
opencompass/configs/datasets/mbpp_cn/mbpp_cn_gen.py
opencompass/configs/datasets/mbpp_cn/mbpp_cn_gen_9114d5.py
opencompass/configs/datasets/mbpp_plus/deprecated_mbpp_plus_gen_94815c.py
opencompass/configs/datasets/mbpp_plus/mbpp_plus_gen.py
opencompass/configs/datasets/mbpp_plus/mbpp_plus_gen_0b836a.py
opencompass/configs/datasets/mbpp_pro/README.md
opencompass/configs/datasets/mbpp_pro/mbpp_pro_gen.py
opencompass/configs/datasets/mbpp_pro/mbpp_pro_gen_3dc067.py
opencompass/configs/datasets/mbpp_pro/mbpp_pro_repeat_gen_3dc067.py
opencompass/configs/datasets/medmcqa/medmcqa_gen.py
opencompass/configs/datasets/medmcqa/medmcqa_gen_60c8f5.py
opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen.py
opencompass/configs/datasets/medmcqa/medmcqa_llmjudge_gen_60c8f5.py
opencompass/configs/datasets/mgsm/README.md
opencompass/configs/datasets/mgsm/mgsm_gen.py
opencompass/configs/datasets/mgsm/mgsm_gen_d967bc.py
opencompass/configs/datasets/mmlu/README.md
opencompass/configs/datasets/mmlu/mmlu_all_sets.py
opencompass/configs/datasets/mmlu/mmlu_clean_ppl.py
opencompass/configs/datasets/mmlu/mmlu_gen.py
opencompass/configs/datasets/mmlu/mmlu_gen_23a9a9.py
opencompass/configs/datasets/mmlu/mmlu_gen_4d595a.py
opencompass/configs/datasets/mmlu/mmlu_gen_5d1409.py
opencompass/configs/datasets/mmlu/mmlu_gen_79e572.py
opencompass/configs/datasets/mmlu/mmlu_gen_a484b3.py
opencompass/configs/datasets/mmlu/mmlu_llm_judge_gen.py
opencompass/configs/datasets/mmlu/mmlu_llmjudge_gen_f4336b.py
opencompass/configs/datasets/mmlu/mmlu_model_postprocess_gen_4d595a.py
opencompass/configs/datasets/mmlu/mmlu_openai_0shot_nocot_llmjudge_gen_216503.py
opencompass/configs/datasets/mmlu/mmlu_openai_simple_evals_gen_b618ea.py
opencompass/configs/datasets/mmlu/mmlu_ppl.py
opencompass/configs/datasets/mmlu/mmlu_ppl_ac766d.py
opencompass/configs/datasets/mmlu/mmlu_stem_0shot_cascade_eval_gen_216503.py
opencompass/configs/datasets/mmlu/mmlu_stem_0shot_gen_216503.py
opencompass/configs/datasets/mmlu/mmlu_stem_0shot_xml_gen_216503.py
opencompass/configs/datasets/mmlu/mmlu_stem_sets.py
opencompass/configs/datasets/mmlu/mmlu_xfinder_gen_4d595a.py
opencompass/configs/datasets/mmlu/mmlu_zero_shot_gen_47e2c0.py
opencompass/configs/datasets/mmlu_cf/mmlu_cf_categories.py
opencompass/configs/datasets/mmlu_cf/mmlu_cf_few_shot.py
opencompass/configs/datasets/mmlu_cf/mmlu_cf_gen.py
opencompass/configs/datasets/mmlu_cf/mmlu_cf_gen_040615.py
opencompass/configs/datasets/mmlu_cf/mmlu_cf_zero_shot.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_0shot_cot_gen_08c1de.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_0shot_nocot_genericllmeval_gen_08c1de.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_biomed_0shot_cot_gen_057927.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_biomed_0shot_nocot_genericllmeval_gen_057927.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_categories.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_few_shot_gen_bfaf90.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_gen.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_gen_cdbebf.py
opencompass/configs/datasets/mmlu_pro/mmlu_pro_llm_judge_gen.py
opencompass/configs/datasets/mmmlu/README.md
opencompass/configs/datasets/mmmlu/mmmlu_5_shot_gen_bcbeb3.py
opencompass/configs/datasets/mmmlu/mmmlu_gen.py
opencompass/configs/datasets/mmmlu/mmmlu_gen_c51a84.py
opencompass/configs/datasets/mmmlu/mmmlu_prompt.py
opencompass/configs/datasets/mmmlu_lite/README.md
opencompass/configs/datasets/mmmlu_lite/mmmlu_lite_gen.py
opencompass/configs/datasets/mmmlu_lite/mmmlu_lite_gen_c51a84.py
opencompass/configs/datasets/multipl_e/multiple_gen.py
opencompass/configs/datasets/multipl_e/multiple_top_ten_gen_f44aaf.py
opencompass/configs/datasets/multipl_e/multiple_top_ten_repeat_gen_0cd6ce.py
opencompass/configs/datasets/musr/README.md
opencompass/configs/datasets/musr/musr_gen.py
opencompass/configs/datasets/musr/musr_gen_3622bb.py
opencompass/configs/datasets/musr/musr_gen_3c6e15.py
opencompass/configs/datasets/musr/musr_gen_b47fd3.py
opencompass/configs/datasets/musr/musr_llm_judge_gen.py
opencompass/configs/datasets/musr/musr_llmjudge_gen_b47fd3.py
opencompass/configs/datasets/narrativeqa/narrativeqa_gen.py
opencompass/configs/datasets/narrativeqa/narrativeqa_gen_a2d88a.py
opencompass/configs/datasets/narrativeqa/narrativeqa_gen_db6413.py
opencompass/configs/datasets/needlebench/readme.md
opencompass/configs/datasets/needlebench/readme_zh-CN.md
opencompass/configs/datasets/needlebench/atc/atc.py
opencompass/configs/datasets/needlebench/atc/atc_choice.py
opencompass/configs/datasets/needlebench/atc/atc_choice_20.py
opencompass/configs/datasets/needlebench/atc/atc_choice_50.py
opencompass/configs/datasets/needlebench/atc/atc_choice_50_en_reasoning.py
opencompass/configs/datasets/needlebench/atc/atc_choice_80.py
opencompass/configs/datasets/needlebench/atc/atc_choice_80_en_reasoning.py
opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_1000k.py
opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_multi_reasoning_1000k.py
opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_multi_retrieval_1000k.py
opencompass/configs/datasets/needlebench/needlebench_1000k/needlebench_single_1000k.py
opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_128k.py
opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_multi_reasoning_128k.py
opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_multi_retrieval_128k.py
opencompass/configs/datasets/needlebench/needlebench_128k/needlebench_single_128k.py
opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_200k.py
opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_multi_reasoning_200k.py
opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_multi_retrieval_200k.py
opencompass/configs/datasets/needlebench/needlebench_200k/needlebench_single_200k.py
opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_256k.py
opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_multi_reasoning_256k.py
opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_multi_retrieval_256k.py
opencompass/configs/datasets/needlebench/needlebench_256k/needlebench_single_256k.py
opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_32k.py
opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_multi_reasoning_32k.py
opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_multi_retrieval_32k.py
opencompass/configs/datasets/needlebench/needlebench_32k/needlebench_single_32k.py
opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_4k.py
opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_multi_reasoning_4k.py
opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_multi_retrieval_4k.py
opencompass/configs/datasets/needlebench/needlebench_4k/needlebench_single_4k.py
opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_8k.py
opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_reasoning_8k.py
opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_retrieval_8k.py
opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_multi_retrieval_compare_batch_8k.py
opencompass/configs/datasets/needlebench/needlebench_8k/needlebench_single_8k.py
opencompass/configs/datasets/needlebench/needlebench_base/needlebench_base_gen.py
opencompass/configs/datasets/needlebench/needlebench_base/needlebench_single.py
opencompass/configs/datasets/needlebench_v2/readme.md
opencompass/configs/datasets/needlebench_v2/readme_zh-CN.md
opencompass/configs/datasets/needlebench_v2/atc/atc_0shot_nocot_2_power_en.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_1000k/needlebench_v2_1000k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_1000k/needlebench_v2_multi_reasoning_1000k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_1000k/needlebench_v2_multi_retrieval_1000k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_1000k/needlebench_v2_single_1000k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_128k/needlebench_v2_128k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_128k/needlebench_v2_multi_reasoning_128k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_128k/needlebench_v2_multi_retrieval_128k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_128k/needlebench_v2_single_128k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_200k/needlebench_v2_200k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_200k/needlebench_v2_multi_reasoning_200k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_200k/needlebench_v2_multi_retrieval_200k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_200k/needlebench_v2_single_200k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_256k/needlebench_v2_256k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_256k/needlebench_v2_multi_reasoning_256k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_256k/needlebench_v2_multi_retrieval_256k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_256k/needlebench_v2_single_256k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_32k/needlebench_v2_32k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_32k/needlebench_v2_multi_reasoning_32k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_32k/needlebench_v2_multi_retrieval_32k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_32k/needlebench_v2_single_32k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_4k/needlebench_v2_4k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_4k/needlebench_v2_multi_reasoning_4k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_4k/needlebench_v2_multi_retrieval_4k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_4k/needlebench_v2_single_4k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_8k/needlebench_v2_8k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_8k/needlebench_v2_multi_reasoning_8k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_8k/needlebench_v2_multi_retrieval_8k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_8k/needlebench_v2_multi_retrieval_compare_batch_8k.py
opencompass/configs/datasets/needlebench_v2/needlebench_v2_8k/needlebench_v2_single_8k.py
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen.py
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_gen_60c8f5.py
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen.py
opencompass/configs/datasets/nejm_ai_benchmark/nejmaibench_llmjudge_gen_60c8f5.py
opencompass/configs/datasets/nq/README.md
opencompass/configs/datasets/nq/nq_gen.py
opencompass/configs/datasets/nq/nq_gen_0356ec.py
opencompass/configs/datasets/nq/nq_gen_2463e2.py
opencompass/configs/datasets/nq/nq_gen_3dcea1.py
opencompass/configs/datasets/nq/nq_gen_68c1c6.py
opencompass/configs/datasets/nq/nq_gen_c788f6.py
opencompass/configs/datasets/nq/nq_open_1shot_gen_01cf41.py
opencompass/configs/datasets/nq/nq_open_1shot_gen_20a989.py
opencompass/configs/datasets/nq/nq_open_1shot_gen_2e45e5.py
opencompass/configs/datasets/nq/nq_open_gen_e93f8a.py
opencompass/configs/datasets/nq/nq_xfinder_gen_3dcea1.py
opencompass/configs/datasets/nq_cn/nqcn_gen.py
opencompass/configs/datasets/nq_cn/nqcn_gen_141737.py
opencompass/configs/datasets/obqa/obqa_gen.py
opencompass/configs/datasets/obqa/obqa_gen_9069e4.py
opencompass/configs/datasets/obqa/obqa_ppl.py
opencompass/configs/datasets/obqa/obqa_ppl_1defe8.py
opencompass/configs/datasets/obqa/obqa_ppl_6aac9e.py
opencompass/configs/datasets/obqa/obqa_ppl_c7c154.py
opencompass/configs/datasets/omni_math/README.md
opencompass/configs/datasets/omni_math/omni_math_cascade_eval_gen_ccf9c0.py
opencompass/configs/datasets/omni_math/omni_math_gen.py
opencompass/configs/datasets/omni_math/omni_math_gen_18cc08.py
opencompass/configs/datasets/omni_math/omni_math_llmverify_gen_ccf9c0.py
opencompass/configs/datasets/piqa/piqa_gen.py
opencompass/configs/datasets/piqa/piqa_gen_1194eb.py
opencompass/configs/datasets/piqa/piqa_ppl.py
opencompass/configs/datasets/piqa/piqa_ppl_0cfff2.py
opencompass/configs/datasets/piqa/piqa_ppl_1cf9f0.py
opencompass/configs/datasets/piqa/piqa_ppl_3431ea.py
opencompass/configs/datasets/promptbench/promptbench_iwslt2017_gen_cbb8c8.py
opencompass/configs/datasets/promptbench/promptbench_math_gen_abf776.py
opencompass/configs/datasets/promptbench/promptbench_squad20_gen_b15d1c.py
opencompass/configs/datasets/promptbench/promptbench_wnli_gen_50662f.py
opencompass/configs/datasets/py150/py150_gen.py
opencompass/configs/datasets/py150/py150_gen_38b13d.py
opencompass/configs/datasets/qabench/qabench_gen.py
opencompass/configs/datasets/qabench/qabench_gen_353ae7.py
opencompass/configs/datasets/qasper/qasper_gen.py
opencompass/configs/datasets/qasper/qasper_gen_a2d88a.py
opencompass/configs/datasets/qasper/qasper_gen_db6413.py
opencompass/configs/datasets/qaspercut/qaspercut_gen.py
opencompass/configs/datasets/qaspercut/qaspercut_gen_a2d88a.py
opencompass/configs/datasets/qaspercut/qaspercut_gen_db6413.py
opencompass/configs/datasets/race/README.md
opencompass/configs/datasets/race/race_cot_gen_d95929.py
opencompass/configs/datasets/race/race_few_shot_gen_a498ed.py
opencompass/configs/datasets/race/race_few_shot_ppl.py
opencompass/configs/datasets/race/race_gen.py
opencompass/configs/datasets/race/race_gen_69ee4f.py
opencompass/configs/datasets/race/race_gen_9302a5.py
opencompass/configs/datasets/race/race_ppl.py
opencompass/configs/datasets/race/race_ppl_5831a0.py
opencompass/configs/datasets/race/race_ppl_a138cd.py
opencompass/configs/datasets/race/race_ppl_abed12.py
opencompass/configs/datasets/realtoxicprompts/realtoxicprompts_gen.py
opencompass/configs/datasets/realtoxicprompts/realtoxicprompts_gen_7605e4.py
opencompass/configs/datasets/realtoxicprompts/realtoxicprompts_gen_ac723c.py
opencompass/configs/datasets/rolebench/instruction_generalization_eng.py
opencompass/configs/datasets/rolebench/instruction_generalization_zh.py
opencompass/configs/datasets/rolebench/role_generalization_eng.py
opencompass/configs/datasets/ruler/README.md
opencompass/configs/datasets/ruler/ruler_128k_gen.py
opencompass/configs/datasets/ruler/ruler_16k_gen.py
opencompass/configs/datasets/ruler/ruler_1m_gen.py
opencompass/configs/datasets/ruler/ruler_256k_gen.py
opencompass/configs/datasets/ruler/ruler_32k_gen.py
opencompass/configs/datasets/ruler/ruler_4k_gen.py
opencompass/configs/datasets/ruler/ruler_512k_gen.py
opencompass/configs/datasets/ruler/ruler_64k_gen.py
opencompass/configs/datasets/ruler/ruler_8k_gen.py
opencompass/configs/datasets/ruler/ruler_combined_gen.py
opencompass/configs/datasets/ruler/ruler_cwe_gen.py
opencompass/configs/datasets/ruler/ruler_fwe_gen.py
opencompass/configs/datasets/ruler/ruler_niah_gen.py
opencompass/configs/datasets/ruler/ruler_qa_gen.py
opencompass/configs/datasets/ruler/ruler_vt_gen.py
opencompass/configs/datasets/s3eval/s3eval.md
opencompass/configs/datasets/s3eval/s3eval_gen.py
opencompass/configs/datasets/s3eval/s3eval_gen_b8ac80.py
opencompass/configs/datasets/safety/safety_gen.py
opencompass/configs/datasets/safety/safety_gen_7ce197.py
opencompass/configs/datasets/sage/README.md
opencompass/configs/datasets/sage/sage_gen.py
opencompass/configs/datasets/sage/sage_val_gen_906a48.py
opencompass/configs/datasets/scibench/scibench_gen.py
opencompass/configs/datasets/scibench/scibench_gen_2b21f3.py
opencompass/configs/datasets/scibench/lib_prompt/atkins_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/atkins_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/calculus_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/calculus_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/chemmc_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/chemmc_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/class_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/class_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/diff_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/diff_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/fund_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/fund_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/matter_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/matter_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/quan_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/quan_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/stat_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/stat_sol.txt
opencompass/configs/datasets/scibench/lib_prompt/thermo_prompt.txt
opencompass/configs/datasets/scibench/lib_prompt/thermo_sol.txt
opencompass/configs/datasets/scicode/README.md
opencompass/configs/datasets/scicode/scicode_gen.py
opencompass/configs/datasets/scicode/scicode_gen_085b98.py
opencompass/configs/datasets/scicode/scicode_gen_62c139.py
opencompass/configs/datasets/scicode/scicode_wbg_gen_085b98.py
opencompass/configs/datasets/siqa/siqa_gen.py
opencompass/configs/datasets/siqa/siqa_gen_18632c.py
opencompass/configs/datasets/siqa/siqa_gen_e78df3.py
opencompass/configs/datasets/siqa/siqa_ppl.py
opencompass/configs/datasets/siqa/siqa_ppl_42bc6e.py
opencompass/configs/datasets/siqa/siqa_ppl_7845b0.py
opencompass/configs/datasets/siqa/siqa_ppl_ced5f6.py
opencompass/configs/datasets/siqa/siqa_ppl_e8d8c5.py
opencompass/configs/datasets/squad20/squad20_gen.py
opencompass/configs/datasets/squad20/squad20_gen_1710bc.py
opencompass/configs/datasets/srbench/srbench_gen.py
opencompass/configs/datasets/storycloze/storycloze_gen.py
opencompass/configs/datasets/storycloze/storycloze_gen_7f656a.py
opencompass/configs/datasets/storycloze/storycloze_ppl.py
opencompass/configs/datasets/storycloze/storycloze_ppl_496661.py
opencompass/configs/datasets/storycloze/storycloze_ppl_afd16f.py
opencompass/configs/datasets/strategyqa/strategyqa_gen.py
opencompass/configs/datasets/strategyqa/strategyqa_gen_1180a7.py
opencompass/configs/datasets/strategyqa/strategyqa_gen_934441.py
opencompass/configs/datasets/subjective/alignbench/alignbench_judgeby_critiquellm.py
opencompass/configs/datasets/subjective/alignbench/alignbench_judgeby_critiquellm_new.py
opencompass/configs/datasets/subjective/alignbench/alignbench_v1_1_judgeby_critiquellm.py
opencompass/configs/datasets/subjective/alignbench/alignbench_v1_1_judgeby_critiquellm_new.py
opencompass/configs/datasets/subjective/alpaca_eval/alpacav2_judgeby_gpt4.py
opencompass/configs/datasets/subjective/alpaca_eval/alpacav2_judgeby_gpt4_bradleyterry.py
opencompass/configs/datasets/subjective/alpaca_eval/alpacav2_judgeby_gpt4_new.py
opencompass/configs/datasets/subjective/arena_hard/README.md
opencompass/configs/datasets/subjective/arena_hard/arena_hard_compare.py
opencompass/configs/datasets/subjective/arena_hard/arena_hard_compare_bradleyterry.py
opencompass/configs/datasets/subjective/arena_hard/arena_hard_compare_new.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/README_pairwise_bt.md
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/multiturn/pairwise_bt_judge.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/multiturn/pairwise_judge.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/multiturn/pointwise_judge.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/singleturn/pairwise_bt_judge.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/singleturn/pairwise_judge.py
opencompass/configs/datasets/subjective/compass_arena_subjective_bench/singleturn/pointwise_judge.py
opencompass/configs/datasets/subjective/compassarena/compassarena_compare.py
opencompass/configs/datasets/subjective/compassarena/compassarena_compare_bradleyterry.py
opencompass/configs/datasets/subjective/compassarena/compassarena_compare_new.py
opencompass/configs/datasets/subjective/compassbench/compassbench_checklist.py
opencompass/configs/datasets/subjective/compassbench/compassbench_compare.py
opencompass/configs/datasets/subjective/compassbench/compassbench_compare_v11.py
opencompass/configs/datasets/subjective/compassbench/compassbench_compare_v11_patch.py
opencompass/configs/datasets/subjective/compassbench/compassbench_compare_v12.py
opencompass/configs/datasets/subjective/flames/README.md
opencompass/configs/datasets/subjective/flames/flames_gen.py
opencompass/configs/datasets/subjective/flames/flames_gen_1a58bb.py
opencompass/configs/datasets/subjective/fofo/README.md
opencompass/configs/datasets/subjective/fofo/fofo_bilingual_judge.py
opencompass/configs/datasets/subjective/fofo/fofo_bilingual_judge_new.py
opencompass/configs/datasets/subjective/fofo/fofo_judge.py
opencompass/configs/datasets/subjective/fofo/fofo_judge_new.py
opencompass/configs/datasets/subjective/followbench/followbench_llmeval.py
opencompass/configs/datasets/subjective/followbench/followbench_llmeval_new.py
opencompass/configs/datasets/subjective/hellobench/README.md
opencompass/configs/datasets/subjective/hellobench/hellobench.py
opencompass/configs/datasets/subjective/judgerbench/judgerbench.py
opencompass/configs/datasets/subjective/multiround/mtbench101_judge.py
opencompass/configs/datasets/subjective/multiround/mtbench101_judge_new.py
opencompass/configs/datasets/subjective/multiround/mtbench_single_judge_diff_temp.py
opencompass/configs/datasets/subjective/multiround/mtbench_single_judge_diff_temp_new.py
opencompass/configs/datasets/subjective/wildbench/wildbench.md
opencompass/configs/datasets/subjective/wildbench/wildbench_pair_judge.py
opencompass/configs/datasets/subjective/wildbench/wildbench_pair_judge_bradleyterry.py
opencompass/configs/datasets/subjective/wildbench/wildbench_pair_judge_new.py
opencompass/configs/datasets/subjective/writingbench/writingbench_judge.py
opencompass/configs/datasets/summedits/summedits_gen.py
opencompass/configs/datasets/summedits/summedits_gen_315438.py
opencompass/configs/datasets/summedits/summedits_gen_4fb38b.py
opencompass/configs/datasets/summedits/summedits_ppl.py
opencompass/configs/datasets/summedits/summedits_ppl_1fbeb6.py
opencompass/configs/datasets/summedits/summedits_ppl_3c30d0.py
opencompass/configs/datasets/summedits/summedits_ppl_fa58ba.py
opencompass/configs/datasets/summscreen/summscreen_gen.py
opencompass/configs/datasets/summscreen/summscreen_gen_653185.py
opencompass/configs/datasets/summscreen/summscreen_gen_aa5eb3.py
opencompass/configs/datasets/supergpqa/supergpqa_cascade_gen_1545c1.py
opencompass/configs/datasets/supergpqa/supergpqa_gen.py
opencompass/configs/datasets/supergpqa/supergpqa_llmjudge_field_gen_1545c1.py
opencompass/configs/datasets/supergpqa/supergpqa_llmjudge_gen_12b8bc.py
opencompass/configs/datasets/taco/README.md
opencompass/configs/datasets/taco/taco_gen.py
opencompass/configs/datasets/taco/taco_gen_c7893a.py
opencompass/configs/datasets/taco/taco_levels_gen_411572.py
opencompass/configs/datasets/teval/README.md
opencompass/configs/datasets/teval/teval_en_gen.py
opencompass/configs/datasets/teval/teval_en_gen_1ac254.py
opencompass/configs/datasets/teval/teval_zh_gen.py
opencompass/configs/datasets/teval/teval_zh_gen_1ac254.py
opencompass/configs/datasets/triviaqa/README.md
opencompass/configs/datasets/triviaqa/triviaqa_gen.py
opencompass/configs/datasets/triviaqa/triviaqa_gen_0356ec.py
opencompass/configs/datasets/triviaqa/triviaqa_gen_2121ce.py
opencompass/configs/datasets/triviaqa/triviaqa_gen_3e39a5.py
opencompass/configs/datasets/triviaqa/triviaqa_gen_429db5.py
opencompass/configs/datasets/triviaqa/triviaqa_gen_d297bb.py
opencompass/configs/datasets/triviaqa/triviaqa_wiki_1shot_gen_20a989.py
opencompass/configs/datasets/triviaqa/triviaqa_wiki_1shot_gen_bc5f21.py
opencompass/configs/datasets/triviaqa/triviaqa_wiki_1shot_gen_c87d61.py
opencompass/configs/datasets/triviaqa/triviaqa_wiki_1shot_gen_eaf81e.py
opencompass/configs/datasets/triviaqa/triviaqa_wiki_gen_d18bf4.py
opencompass/configs/datasets/triviaqarc/triviaqarc_gen.py
opencompass/configs/datasets/triviaqarc/triviaqarc_gen_a2d88a.py
opencompass/configs/datasets/triviaqarc/triviaqarc_gen_db6413.py
opencompass/configs/datasets/truthfulqa/truthfulqa_gen.py
opencompass/configs/datasets/truthfulqa/truthfulqa_gen_1e7d8d.py
opencompass/configs/datasets/truthfulqa/truthfulqa_gen_5ddc62.py
opencompass/configs/datasets/tydiqa/tydiqa_gen.py
opencompass/configs/datasets/tydiqa/tydiqa_gen_978d2a.py
opencompass/configs/datasets/wikibench/wikibench_few_shot_ppl_c23d79.py
opencompass/configs/datasets/wikibench/wikibench_gen.py
opencompass/configs/datasets/wikibench/wikibench_gen_0978ad.py
opencompass/configs/datasets/wikibench/wikibench_gen_f96ece.py
opencompass/configs/datasets/wikitext/wikitext_103_raw_ppl.py
opencompass/configs/datasets/wikitext/wikitext_103_raw_ppl_752e2a.py
opencompass/configs/datasets/wikitext/wikitext_2_raw_ppl.py
opencompass/configs/datasets/wikitext/wikitext_2_raw_ppl_752e2a.py
opencompass/configs/datasets/winograd/winograd_ppl.py
opencompass/configs/datasets/winograd/winograd_ppl_8f3049.py
opencompass/configs/datasets/winograd/winograd_ppl_b6c7ed.py
opencompass/configs/datasets/winogrande/README.md
opencompass/configs/datasets/winogrande/deprecated_winogrande_gen_a9ede5.py
opencompass/configs/datasets/winogrande/winogrande_5shot_gen_6447e6.py
opencompass/configs/datasets/winogrande/winogrande_5shot_gen_b36770.py
opencompass/configs/datasets/winogrande/winogrande_5shot_ll_252f01.py
opencompass/configs/datasets/winogrande/winogrande_gen.py
opencompass/configs/datasets/winogrande/winogrande_gen_458220.py
opencompass/configs/datasets/winogrande/winogrande_gen_a027b6.py
opencompass/configs/datasets/winogrande/winogrande_ll.py
opencompass/configs/datasets/winogrande/winogrande_ll_c5cf57.py
opencompass/configs/datasets/winogrande/winogrande_ppl_55a66e.py
opencompass/configs/datasets/winogrande/winogrande_ppl_9307fd.py
opencompass/configs/datasets/xiezhi/xiezhi_gen.py
opencompass/configs/datasets/xiezhi/xiezhi_gen_b86cf5.py
opencompass/configs/datasets/xiezhi/xiezhi_ppl.py
opencompass/configs/datasets/xiezhi/xiezhi_ppl_ea6bd7.py
opencompass/configs/models/accessory/accessory_llama2_7b.py
opencompass/configs/models/accessory/accessory_mixtral_8x7b.py
opencompass/configs/models/accessory/accessory_sphinx_v2_1k.py
opencompass/configs/models/alaya/alaya.py
opencompass/configs/models/aquila/hf_aquila2_34b.py
opencompass/configs/models/aquila/hf_aquila2_7b.py
opencompass/configs/models/aquila/hf_aquilachat2_34b.py
opencompass/configs/models/aquila/hf_aquilachat2_34b_16k.py
opencompass/configs/models/aquila/hf_aquilachat2_7b.py
opencompass/configs/models/aquila/hf_aquilachat2_7b_16k.py
opencompass/configs/models/baichuan/hf_baichuan2_13b_base.py
opencompass/configs/models/baichuan/hf_baichuan2_13b_chat.py
opencompass/configs/models/baichuan/hf_baichuan2_7b_base.py
opencompass/configs/models/baichuan/hf_baichuan2_7b_chat.py
opencompass/configs/models/baichuan/hf_baichuan_13b_base.py
opencompass/configs/models/baichuan/hf_baichuan_13b_chat.py
opencompass/configs/models/baichuan/hf_baichuan_7b.py
opencompass/configs/models/baichuan/hf_baichuan_m1_14b_base.py
opencompass/configs/models/baichuan/hf_baichuan_m1_14b_instruct.py
opencompass/configs/models/bailing_api/bailing-lite-1116.py
opencompass/configs/models/bailing_api/bailing-pro-1120.py
opencompass/configs/models/bluelm/bluelm_3b.py
opencompass/configs/models/bluelm/hf_bluelm_7b_base.py
opencompass/configs/models/bluelm/hf_bluelm_7b_base_32k.py
opencompass/configs/models/bluelm/hf_bluelm_7b_chat.py
opencompass/configs/models/bluelm/hf_bluelm_7b_chat_32k.py
opencompass/configs/models/chatglm/hf_chatglm2_6b.py
opencompass/configs/models/chatglm/hf_chatglm3_6b.py
opencompass/configs/models/chatglm/hf_chatglm3_6b_32k.py
opencompass/configs/models/chatglm/hf_chatglm3_6b_base.py
opencompass/configs/models/chatglm/hf_chatglm_6b.py
opencompass/configs/models/chatglm/hf_glm4_9b.py
opencompass/configs/models/chatglm/hf_glm4_9b_chat.py
opencompass/configs/models/chatglm/lmdeploy_glm4_9b.py
opencompass/configs/models/chatglm/lmdeploy_glm4_9b_chat.py
opencompass/configs/models/chatglm/vllm_chatglm3_6b.py
opencompass/configs/models/chatglm/vllm_chatglm3_6b_32k.py
opencompass/configs/models/chatglm/vllm_glm4_9b_chat.py
opencompass/configs/models/claude/claude.py
opencompass/configs/models/claude/claude2.py
opencompass/configs/models/codegeex2/hf_codegeex2_6b.py
opencompass/configs/models/codellama/hf_codellama_13b.py
opencompass/configs/models/codellama/hf_codellama_13b_instruct.py
opencompass/configs/models/codellama/hf_codellama_13b_python.py
opencompass/configs/models/codellama/hf_codellama_34b.py
opencompass/configs/models/codellama/hf_codellama_34b_instruct.py
opencompass/configs/models/codellama/hf_codellama_34b_python.py
opencompass/configs/models/codellama/hf_codellama_70b.py
opencompass/configs/models/codellama/hf_codellama_70b_instruct.py
opencompass/configs/models/codellama/hf_codellama_70b_python.py
opencompass/configs/models/codellama/hf_codellama_7b.py
opencompass/configs/models/codellama/hf_codellama_7b_instruct.py
opencompass/configs/models/codellama/hf_codellama_7b_python.py
opencompass/configs/models/deepseek/deepseek_r1_streaming.py
opencompass/configs/models/deepseek/hf_deepseek_67b_base.py
opencompass/configs/models/deepseek/hf_deepseek_67b_chat.py
opencompass/configs/models/deepseek/hf_deepseek_7b_base.py
opencompass/configs/models/deepseek/hf_deepseek_7b_chat.py
opencompass/configs/models/deepseek/hf_deepseek_coder_1_3b_instruct.py
opencompass/configs/models/deepseek/hf_deepseek_coder_33b_instruct.py
opencompass/configs/models/deepseek/hf_deepseek_coder_6_7b_instruct.py
opencompass/configs/models/deepseek/hf_deepseek_moe_16b_base.py
opencompass/configs/models/deepseek/hf_deepseek_moe_16b_chat.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_70b.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_llama_8b.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_14b.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_1_5b.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_32b.py
opencompass/configs/models/deepseek/hf_deepseek_r1_distill_qwen_7b.py
opencompass/configs/models/deepseek/hf_deepseek_v2.py
opencompass/configs/models/deepseek/hf_deepseek_v2_chat.py
opencompass/configs/models/deepseek/hf_deepseek_v2_lite.py
opencompass/configs/models/deepseek/hf_deepseek_v2_lite_chat.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_67b_base.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_67b_chat.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_7b_base.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_7b_chat.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_70b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_llama_8b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_14b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_1_5b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_32b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_r1_distill_qwen_7b.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_series.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_v2.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_v2_5.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_v2_5_1210.py
opencompass/configs/models/deepseek/lmdeploy_deepseek_v2_lite.py
opencompass/configs/models/deepseek/vllm_deepseek_67b_chat.py
opencompass/configs/models/deepseek/vllm_deepseek_7b_chat.py
opencompass/configs/models/deepseek/vllm_deepseek_moe_16b_base.py
opencompass/configs/models/deepseek/vllm_deepseek_moe_16b_chat.py
opencompass/configs/models/falcon/hf_falcon_40b.py
opencompass/configs/models/falcon/hf_falcon_7b.py
opencompass/configs/models/gemini/gemini_1_5_flash.py
opencompass/configs/models/gemini/gemini_1_5_pro.py
opencompass/configs/models/gemini/gemini_pro.py
opencompass/configs/models/gemma/hf_gemma2_27b.py
opencompass/configs/models/gemma/hf_gemma2_27b_it.py
opencompass/configs/models/gemma/hf_gemma2_2b.py
opencompass/configs/models/gemma/hf_gemma2_2b_it.py
opencompass/configs/models/gemma/hf_gemma2_9b.py
opencompass/configs/models/gemma/hf_gemma2_9b_it.py
opencompass/configs/models/gemma/hf_gemma_2b.py
opencompass/configs/models/gemma/hf_gemma_2b_it.py
opencompass/configs/models/gemma/hf_gemma_7b.py
opencompass/configs/models/gemma/hf_gemma_7b_it.py
opencompass/configs/models/gemma/lmdeploy_gemma_27b.py
opencompass/configs/models/gemma/lmdeploy_gemma_27b_it.py
opencompass/configs/models/gemma/lmdeploy_gemma_9b.py
opencompass/configs/models/gemma/lmdeploy_gemma_9b_it.py
opencompass/configs/models/gemma/vllm_gemma_2b.py
opencompass/configs/models/gemma/vllm_gemma_2b_it.py
opencompass/configs/models/gemma/vllm_gemma_3_12b_it.py
opencompass/configs/models/gemma/vllm_gemma_3_27b_it.py
opencompass/configs/models/gemma/vllm_gemma_3_4b_it.py
opencompass/configs/models/gemma/vllm_gemma_7b.py
opencompass/configs/models/gemma/vllm_gemma_7b_it.py
opencompass/configs/models/hf_internlm/README.md
opencompass/configs/models/hf_internlm/hf_internlm2_1_8b.py
opencompass/configs/models/hf_internlm/hf_internlm2_20b.py
opencompass/configs/models/hf_internlm/hf_internlm2_5_1_8b_chat.py
opencompass/configs/models/hf_internlm/hf_internlm2_5_20b_chat.py
opencompass/configs/models/hf_internlm/hf_internlm2_5_7b.py
opencompass/configs/models/hf_internlm/hf_internlm2_5_7b_chat.py
opencompass/configs/models/hf_internlm/hf_internlm2_7b.py
opencompass/configs/models/hf_internlm/hf_internlm2_base_20b.py
opencompass/configs/models/hf_internlm/hf_internlm2_base_7b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_1_8b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_1_8b_sft.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_20b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_20b_sft.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_20b_with_system.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_7b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_7b_sft.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_7b_with_system.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_math_20b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_math_20b_with_system.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_math_7b.py
opencompass/configs/models/hf_internlm/hf_internlm2_chat_math_7b_with_system.py
opencompass/configs/models/hf_internlm/hf_internlm2_math_20b.py
opencompass/configs/models/hf_internlm/hf_internlm2_math_7b.py
opencompass/configs/models/hf_internlm/hf_internlm3_8b_instruct.py
opencompass/configs/models/hf_internlm/hf_internlm_20b.py
opencompass/configs/models/hf_internlm/hf_internlm_7b.py
opencompass/configs/models/hf_internlm/hf_internlm_chat_20b.py
opencompass/configs/models/hf_internlm/hf_internlm_chat_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_1_8b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_20b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_5_1_8b_chat.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_5_20b_chat.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_5_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_5_7b_chat.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_5_7b_chat_1m.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_base_20b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_base_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_1_8b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_1_8b_sft.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_20b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_20b_sft.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_chat_7b_sft.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm2_series.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm3_8b_instruct_128k.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm_20b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm_chat_20b.py
opencompass/configs/models/hf_internlm/lmdeploy_internlm_chat_7b.py
opencompass/configs/models/hf_internlm/lmdeploy_oreal_32b.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_1_8b.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_1_8b_sft.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_20b.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_20b_sft.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_7b.py
opencompass/configs/models/hf_internlm/vllm_internlm2_chat_7b_sft.py
opencompass/configs/models/hf_internlm/vllm_internlm2_series.py
opencompass/configs/models/hf_llama/hf_llama2_13b.py
opencompass/configs/models/hf_llama/hf_llama2_13b_chat.py
opencompass/configs/models/hf_llama/hf_llama2_70b.py
opencompass/configs/models/hf_llama/hf_llama2_70b_chat.py
opencompass/configs/models/hf_llama/hf_llama2_7b.py
opencompass/configs/models/hf_llama/hf_llama2_7b_chat.py
opencompass/configs/models/hf_llama/hf_llama3_1_70b_instruct.py
opencompass/configs/models/hf_llama/hf_llama3_1_8b.py
opencompass/configs/models/hf_llama/hf_llama3_1_8b_instruct.py
opencompass/configs/models/hf_llama/hf_llama3_2_3b_instruct.py
opencompass/configs/models/hf_llama/hf_llama3_70b.py
opencompass/configs/models/hf_llama/hf_llama3_70b_instruct.py
opencompass/configs/models/hf_llama/hf_llama3_8b.py
opencompass/configs/models/hf_llama/hf_llama3_8b_instruct.py
opencompass/configs/models/hf_llama/hf_llama_13b.py
opencompass/configs/models/hf_llama/hf_llama_30b.py
opencompass/configs/models/hf_llama/hf_llama_65b.py
opencompass/configs/models/hf_llama/hf_llama_7b.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_13b.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_13b_chat.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_70b.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_70b_chat.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_7b.py
opencompass/configs/models/hf_llama/lmdeploy_llama2_7b_chat.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_1_70b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_1_8b.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_1_8b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_2_3b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_3_70b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_70b.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_70b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_8b.py
opencompass/configs/models/hf_llama/lmdeploy_llama3_8b_instruct.py
opencompass/configs/models/hf_llama/lmdeploy_llama_13b.py
opencompass/configs/models/hf_llama/lmdeploy_llama_30b.py
opencompass/configs/models/hf_llama/lmdeploy_llama_65b.py
opencompass/configs/models/hf_llama/lmdeploy_llama_7b.py
opencompass/configs/models/hf_llama/vllm_llama_series.py
opencompass/configs/models/huatuogpt/hf_huatuogpt2_13b.py
opencompass/configs/models/huatuogpt/hf_huatuogpt2_7b.py
opencompass/configs/models/huatuogpt/hf_huatuogpt_o1_7b.py
opencompass/configs/models/huatuogpt/hf_huatuogpt_o1_8b.py
opencompass/configs/models/internlm/internlm_7b.py
opencompass/configs/models/interns1/intern_s1.py
opencompass/configs/models/internvl/lmdeploy_internvl_2_5_38b.py
opencompass/configs/models/internvl/lmdeploy_internvl_2_5_8b.py
opencompass/configs/models/judge_llm/auto_j/hf_autoj_bilingual_6b.py
opencompass/configs/models/judge_llm/auto_j/hf_autoj_eng_13b.py
opencompass/configs/models/judge_llm/auto_j/hf_autoj_eng_13b_4bit.py
opencompass/configs/models/judge_llm/auto_j/hf_autoj_scen_classifier.py
opencompass/configs/models/judge_llm/judgelm/hf_judgelm_13b_v1.py
opencompass/configs/models/judge_llm/judgelm/hf_judgelm_33b_v1.py
opencompass/configs/models/judge_llm/judgelm/hf_judgelm_7b_v1.py
opencompass/configs/models/judge_llm/pandalm/hf_alpaca_pandalm_7b_v1.py
opencompass/configs/models/judge_llm/pandalm/hf_pandalm_7b_v1.py
opencompass/configs/models/lemur/lemur_70b_chat.py
opencompass/configs/models/lingowhale/hf_lingowhale_8b.py
opencompass/configs/models/mistral/hf_ministral_8b_instruct_2410.py
opencompass/configs/models/mistral/hf_mistral_7b_instruct_v0_1.py
opencompass/configs/models/mistral/hf_mistral_7b_instruct_v0_2.py
opencompass/configs/models/mistral/hf_mistral_7b_instruct_v0_3.py
opencompass/configs/models/mistral/hf_mistral_7b_v0_1.py
opencompass/configs/models/mistral/hf_mistral_7b_v0_2.py
opencompass/configs/models/mistral/hf_mistral_7b_v0_3.py
opencompass/configs/models/mistral/hf_mistral_nemo_instruct_2407.py
opencompass/configs/models/mistral/hf_mistral_small_instruct_2409.py
opencompass/configs/models/mistral/hf_mixtral_8x22b_instruct_v0_1.py
opencompass/configs/models/mistral/hf_mixtral_8x22b_v0_1.py
opencompass/configs/models/mistral/hf_mixtral_8x7b_instruct_v0_1.py
opencompass/configs/models/mistral/hf_mixtral_8x7b_v0_1.py
opencompass/configs/models/mistral/lmdeploy_ministral_8b_instruct_2410.py
opencompass/configs/models/mistral/lmdeploy_mistral_7b_instruct_v0_3.py
opencompass/configs/models/mistral/lmdeploy_mistral_large_instruct_2411.py
opencompass/configs/models/mistral/lmdeploy_mistral_nemo_instruct_2407.py
opencompass/configs/models/mistral/lmdeploy_mistral_small_instruct_2409.py
opencompass/configs/models/mistral/lmdeploy_mixtral_8x22b_instruct_v0_1.py
opencompass/configs/models/mistral/lmdeploy_mixtral_large_instruct_2407.py
opencompass/configs/models/mistral/mixtral_8x7b_32k.py
opencompass/configs/models/mistral/vllm_mistral_7b_instruct_v0_1.py
opencompass/configs/models/mistral/vllm_mistral_7b_instruct_v0_2.py
opencompass/configs/models/mistral/vllm_mistral_7b_v0_1.py
opencompass/configs/models/mistral/vllm_mistral_7b_v0_2.py
opencompass/configs/models/mistral/vllm_mixtral_8x22b_instruct_v0_1.py
opencompass/configs/models/mistral/vllm_mixtral_8x22b_v0_1.py
opencompass/configs/models/mistral/vllm_mixtral_8x7b_instruct_v0_1.py
opencompass/configs/models/mistral/vllm_mixtral_8x7b_v0_1.py
opencompass/configs/models/mistral/vllm_mixtral_large_instruct_2407.py
opencompass/configs/models/moonshot/kimi_k2.py
opencompass/configs/models/moonshot/kimi_k2_streaming.py
opencompass/configs/models/moss/hf_moss_moon_003_base.py
opencompass/configs/models/moss/hf_moss_moon_003_sft.py
opencompass/configs/models/mpt/hf_mpt_7b.py
opencompass/configs/models/mpt/hf_mpt_instruct_7b.py
opencompass/configs/models/ms_internlm/ms_internlm_chat_7b_8k.py
opencompass/configs/models/nanbeige/hf_nanbeige2_16b_chat.py
opencompass/configs/models/nanbeige/hf_nanbeige2_8b_chat.py
opencompass/configs/models/nanbeige/hf_nanbeige_16b_chat.py
opencompass/configs/models/nvidia/lmdeploy_nemotron_70b_instruct_hf.py
opencompass/configs/models/openai/gpt_3_5_turbo.py
opencompass/configs/models/openai/gpt_3_5_turbo_0125.py
opencompass/configs/models/openai/gpt_4.py
opencompass/configs/models/openai/gpt_4o_2024_05_13.py
opencompass/configs/models/openai/o1_mini_2024_09_12.py
opencompass/configs/models/openai/o1_preview_2024_09_12.py
opencompass/configs/models/openbmb/hf_minicpm3_4b.py
opencompass/configs/models/openbmb/hf_minicpm_2b_dpo_fp32.py
opencompass/configs/models/openbmb/hf_minicpm_2b_sft_bf16.py
opencompass/configs/models/openbmb/hf_minicpm_2b_sft_fp32.py
opencompass/configs/models/opt/hf_opt_125m.py
opencompass/configs/models/opt/hf_opt_350m.py
opencompass/configs/models/others/hf_abel_7b_001.py
opencompass/configs/models/others/hf_abel_7b_002.py
opencompass/configs/models/others/hf_arithmo_mistral_7b.py
opencompass/configs/models/others/hf_command_r_plus.py
opencompass/configs/models/others/hf_dbrx_base.py
opencompass/configs/models/others/hf_dbrx_instruct.py
opencompass/configs/models/others/hf_dolphin_21_mistral_7b.py
opencompass/configs/models/others/hf_fashiongpt_70b_v11.py
opencompass/configs/models/others/hf_gsm8k_rft_llama7b2_u13b.py
opencompass/configs/models/others/hf_metamath_7b_v1_0.py
opencompass/configs/models/others/hf_metamath_llemma_7b.py
opencompass/configs/models/others/hf_metamath_mistral_7b.py
opencompass/configs/models/others/hf_openchat_35_0106.py
opencompass/configs/models/others/hf_openchat_35_1210.py
opencompass/configs/models/others/hf_orionstar_14b_base.py
opencompass/configs/models/others/hf_orionstar_yi_34b_chat.py
opencompass/configs/models/others/hf_phi_2.py
opencompass/configs/models/others/hf_telechat_12b_v2.py
opencompass/configs/models/others/hf_telechat_52b.py
opencompass/configs/models/others/hf_telechat_7b.py
opencompass/configs/models/others/hf_yayi2_30b_base.py
opencompass/configs/models/others/vllm_dbrx_instruct.py
opencompass/configs/models/others/vllm_orionstar_14b_longchat.py
opencompass/configs/models/phi/hf_phi_3_5_MoE_instruct.py
opencompass/configs/models/phi/hf_phi_3_5_mini_instruct.py
opencompass/configs/models/phi/hf_phi_3_medium_4k_instruct.py
opencompass/configs/models/phi/hf_phi_3_mini_4k_instruct.py
opencompass/configs/models/phi/hf_phi_3_small_8k_instruct.py
opencompass/configs/models/phi/hf_phi_4.py
opencompass/configs/models/pulse/hf_pulse_7b.py
opencompass/configs/models/qwen/README.md
opencompass/configs/models/qwen/hf_qwen1_5_0_5b.py
opencompass/configs/models/qwen/hf_qwen1_5_0_5b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_110b.py
opencompass/configs/models/qwen/hf_qwen1_5_110b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_14b.py
opencompass/configs/models/qwen/hf_qwen1_5_14b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_1_8b.py
opencompass/configs/models/qwen/hf_qwen1_5_1_8b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_32b.py
opencompass/configs/models/qwen/hf_qwen1_5_32b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_4b.py
opencompass/configs/models/qwen/hf_qwen1_5_4b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_72b.py
opencompass/configs/models/qwen/hf_qwen1_5_72b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_7b.py
opencompass/configs/models/qwen/hf_qwen1_5_7b_chat.py
opencompass/configs/models/qwen/hf_qwen1_5_moe_a2_7b.py
opencompass/configs/models/qwen/hf_qwen1_5_moe_a2_7b_chat.py
opencompass/configs/models/qwen/hf_qwen2_0_5b.py
opencompass/configs/models/qwen/hf_qwen2_0_5b_instruct.py
opencompass/configs/models/qwen/hf_qwen2_1_5b.py
opencompass/configs/models/qwen/hf_qwen2_1_5b_instruct.py
opencompass/configs/models/qwen/hf_qwen2_57b_a14b.py
opencompass/configs/models/qwen/hf_qwen2_72b.py
opencompass/configs/models/qwen/hf_qwen2_7b.py
opencompass/configs/models/qwen/hf_qwen2_7b_instruct.py
opencompass/configs/models/qwen/hf_qwen_14b.py
opencompass/configs/models/qwen/hf_qwen_14b_chat.py
opencompass/configs/models/qwen/hf_qwen_1_8b.py
opencompass/configs/models/qwen/hf_qwen_1_8b_chat.py
opencompass/configs/models/qwen/hf_qwen_72b.py
opencompass/configs/models/qwen/hf_qwen_72b_chat.py
opencompass/configs/models/qwen/hf_qwen_7b.py
opencompass/configs/models/qwen/hf_qwen_7b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_110b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_110b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_14b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_14b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_1_8b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_1_8b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_32b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_32b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_4b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_4b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_72b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_72b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_7b.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_7b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen1_5_series.py
opencompass/configs/models/qwen/lmdeploy_qwen2_1_5b.py
opencompass/configs/models/qwen/lmdeploy_qwen2_1_5b_instruct.py
opencompass/configs/models/qwen/lmdeploy_qwen2_72b.py
opencompass/configs/models/qwen/lmdeploy_qwen2_72b_instruct.py
opencompass/configs/models/qwen/lmdeploy_qwen2_7b.py
opencompass/configs/models/qwen/lmdeploy_qwen2_7b_instruct.py
opencompass/configs/models/qwen/lmdeploy_qwen2_series.py
opencompass/configs/models/qwen/lmdeploy_qwen_14b.py
opencompass/configs/models/qwen/lmdeploy_qwen_14b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen_1_8b.py
opencompass/configs/models/qwen/lmdeploy_qwen_1_8b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen_72b.py
opencompass/configs/models/qwen/lmdeploy_qwen_72b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen_7b.py
opencompass/configs/models/qwen/lmdeploy_qwen_7b_chat.py
opencompass/configs/models/qwen/lmdeploy_qwen_series.py
opencompass/configs/models/qwen/ms_qwen_7b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_0_5b.py
opencompass/configs/models/qwen/vllm_qwen1_5_0_5b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_110b.py
opencompass/configs/models/qwen/vllm_qwen1_5_110b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_14b.py
opencompass/configs/models/qwen/vllm_qwen1_5_14b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_1_8b.py
opencompass/configs/models/qwen/vllm_qwen1_5_1_8b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_32b.py
opencompass/configs/models/qwen/vllm_qwen1_5_32b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_4b.py
opencompass/configs/models/qwen/vllm_qwen1_5_4b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_72b.py
opencompass/configs/models/qwen/vllm_qwen1_5_72b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_7b.py
opencompass/configs/models/qwen/vllm_qwen1_5_7b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_moe_a2_7b.py
opencompass/configs/models/qwen/vllm_qwen1_5_moe_a2_7b_chat.py
opencompass/configs/models/qwen/vllm_qwen1_5_series.py
opencompass/configs/models/qwen/vllm_qwen2_0_5b.py
opencompass/configs/models/qwen/vllm_qwen2_0_5b_instruct.py
opencompass/configs/models/qwen/vllm_qwen2_1_5b.py
opencompass/configs/models/qwen/vllm_qwen2_1_5b_instruct.py
opencompass/configs/models/qwen/vllm_qwen2_57b_a14b_instruct.py
opencompass/configs/models/qwen/vllm_qwen2_72b.py
opencompass/configs/models/qwen/vllm_qwen2_72b_instruct.py
opencompass/configs/models/qwen/vllm_qwen2_7b.py
opencompass/configs/models/qwen/vllm_qwen2_7b_instruct.py
opencompass/configs/models/qwen/vllm_qwen2_series.py
opencompass/configs/models/qwen/vllm_qwen_14b.py
opencompass/configs/models/qwen/vllm_qwen_14b_chat.py
opencompass/configs/models/qwen/vllm_qwen_1_8b.py
opencompass/configs/models/qwen/vllm_qwen_1_8b_chat.py
opencompass/configs/models/qwen/vllm_qwen_72b.py
opencompass/configs/models/qwen/vllm_qwen_72b_chat.py
opencompass/configs/models/qwen/vllm_qwen_7b.py
opencompass/configs/models/qwen/vllm_qwen_7b_chat.py
opencompass/configs/models/qwen/vllm_qwen_series.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_0_5b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_14b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_1_5b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_32b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_3b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_72b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen2_5_7b_instruct.py
opencompass/configs/models/qwen2_5/hf_qwen_2_5_14b.py
opencompass/configs/models/qwen2_5/hf_qwen_2_5_32b.py
opencompass/configs/models/qwen2_5/hf_qwen_2_5_7b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_0_5b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_14b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_14b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_1_5b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_1_5b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_32b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_32b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_3b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_72b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_72b_instruct.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_7b.py
opencompass/configs/models/qwen2_5/lmdeploy_qwen2_5_7b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_0_5b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_14b_instruct_128k.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_1_5b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_32b_instruct_128k.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_3b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_72b_instruct_128k.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct.py
opencompass/configs/models/qwen2_5/vllm_qwen2_5_7b_instruct_128k.py
opencompass/configs/models/qwen3/lmdeploy_qwen3_0_6b.py
opencompass/configs/models/qwq/lmdeploy_qwq_32b.py
opencompass/configs/models/qwq/lmdeploy_qwq_32b_preview.py
opencompass/configs/models/rwkv/rwkv5_3b.py
opencompass/configs/models/skywork/hf_skywork_13b.py
opencompass/configs/models/skywork/lmdeploy_skywork_o1_open_llama3_1_8b_instruct.py
opencompass/configs/models/tigerbot/hf_tigerbot_13b_base_v1.py
opencompass/configs/models/tigerbot/hf_tigerbot_13b_base_v2.py
opencompass/configs/models/tigerbot/hf_tigerbot_13b_chat_v1.py
opencompass/configs/models/tigerbot/hf_tigerbot_13b_chat_v2.py
opencompass/configs/models/tigerbot/hf_tigerbot_70b_base.py
opencompass/configs/models/tigerbot/hf_tigerbot_70b_chat_v2.py
opencompass/configs/models/tigerbot/hf_tigerbot_70b_chat_v3.py
opencompass/configs/models/tigerbot/hf_tigerbot_7b_base.py
opencompass/configs/models/tigerbot/hf_tigerbot_7b_base_v3.py
opencompass/configs/models/tigerbot/hf_tigerbot_7b_chat_v3.py
opencompass/configs/models/tigerbot/hf_tigerbot_7b_sft.py
opencompass/configs/models/vicuna/hf_vicuna_13b_v13.py
opencompass/configs/models/vicuna/hf_vicuna_13b_v15.py
opencompass/configs/models/vicuna/hf_vicuna_13b_v15_16k.py
opencompass/configs/models/vicuna/hf_vicuna_33b_v13.py
opencompass/configs/models/vicuna/hf_vicuna_7b_v13.py
opencompass/configs/models/vicuna/hf_vicuna_7b_v15.py
opencompass/configs/models/vicuna/hf_vicuna_7b_v15_16k.py
opencompass/configs/models/vicuna/vllm_vicuna_13b_v15_16k.py
opencompass/configs/models/vicuna/vllm_vicuna_7b_v15_16k.py
opencompass/configs/models/wizardcoder/hf_wizardcoder_15b.py
opencompass/configs/models/wizardcoder/hf_wizardcoder_1b.py
opencompass/configs/models/wizardcoder/hf_wizardcoder_3b.py
opencompass/configs/models/wizardcoder/hf_wizardcoder_python_13b.py
opencompass/configs/models/wizardcoder/hf_wizardcoder_python_34b.py
opencompass/configs/models/wizardlm/hf_wizardlm_13b_v1_2.py
opencompass/configs/models/wizardlm/hf_wizardlm_70b_v1_0.py
opencompass/configs/models/wizardlm/hf_wizardlm_7b_v1_0.py
opencompass/configs/models/wizardlm/hf_wizardmath_7b_v1_0.py
opencompass/configs/models/wizardlm/hf_wizardmath_7b_v1_1.py
opencompass/configs/models/wizardlm/vllm_wizardlm_13b_v1_2.py
opencompass/configs/models/wizardlm/vllm_wizardlm_70b_v1_0.py
opencompass/configs/models/wizardlm/vllm_wizardlm_7b_v1_0.py
opencompass/configs/models/yi/hf_yi_1_5_34b.py
opencompass/configs/models/yi/hf_yi_1_5_34b_chat.py
opencompass/configs/models/yi/hf_yi_1_5_6b.py
opencompass/configs/models/yi/hf_yi_1_5_6b_chat.py
opencompass/configs/models/yi/hf_yi_1_5_9b.py
opencompass/configs/models/yi/hf_yi_1_5_9b_chat.py
opencompass/configs/models/yi/hf_yi_34b.py
opencompass/configs/models/yi/hf_yi_34b_chat.py
opencompass/configs/models/yi/hf_yi_6b.py
opencompass/configs/models/yi/hf_yi_6b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_1_5_34b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_1_5_6b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_1_5_9b.py
opencompass/configs/models/yi/lmdeploy_yi_1_5_9b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_34b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_6b_chat.py
opencompass/configs/models/yi/lmdeploy_yi_series.py
opencompass/configs/models/zephyr/hf_zephyr_7b_beta.py
opencompass/configs/models/zephyr/vllm_zephyr_7b_beta.py
opencompass/configs/summarizers/OlympiadBench.py
opencompass/configs/summarizers/PMMEval.py
opencompass/configs/summarizers/agent_bench.py
opencompass/configs/summarizers/charm_reason.py
opencompass/configs/summarizers/chat_OC15.py
opencompass/configs/summarizers/chat_OC15_multi_faceted.py
opencompass/configs/summarizers/cibench.py
opencompass/configs/summarizers/code_passk.py
opencompass/configs/summarizers/compassbench_v1_1_objective.py
opencompass/configs/summarizers/compassbench_v1_1_objective_public.py
opencompass/configs/summarizers/compassbench_v1_3_objective.py
opencompass/configs/summarizers/compassbench_v1_objective.py
opencompass/configs/summarizers/contamination.py
opencompass/configs/summarizers/example.py
opencompass/configs/summarizers/infinitebench.py
opencompass/configs/summarizers/internlm2_keyset.py
opencompass/configs/summarizers/judgedataset_all.py
opencompass/configs/summarizers/judgerbenchv2.py
opencompass/configs/summarizers/lawbench.py
opencompass/configs/summarizers/leaderboard.py
opencompass/configs/summarizers/leval.py
opencompass/configs/summarizers/longbench.py
opencompass/configs/summarizers/longeval_v2.py
opencompass/configs/summarizers/lveval.py
opencompass/configs/summarizers/math_agent.py
opencompass/configs/summarizers/math_baseline.py
opencompass/configs/summarizers/mathbench.py
opencompass/configs/summarizers/mathbench_v1.py
opencompass/configs/summarizers/medium.py
opencompass/configs/summarizers/mmlu_cf.py
opencompass/configs/summarizers/mmlu_pro.py
opencompass/configs/summarizers/mmmlu.py
opencompass/configs/summarizers/mmmlu_lite.py
opencompass/configs/summarizers/needlebench.py
opencompass/configs/summarizers/plugineval.py
opencompass/configs/summarizers/rewardbench.py
opencompass/configs/summarizers/ruler.py
opencompass/configs/summarizers/scicode.py
opencompass/configs/summarizers/simpleqa.py
opencompass/configs/summarizers/small.py
opencompass/configs/summarizers/subjective.py
opencompass/configs/summarizers/teval.py
opencompass/configs/summarizers/tiny.py
opencompass/configs/summarizers/groups/GaokaoBench.py
opencompass/configs/summarizers/groups/MMLUArabic.py
opencompass/configs/summarizers/groups/OlympiadBench.py
opencompass/configs/summarizers/groups/PHYSICS.py
opencompass/configs/summarizers/groups/PMMEval.py
opencompass/configs/summarizers/groups/agieval.py
opencompass/configs/summarizers/groups/babilong.py
opencompass/configs/summarizers/groups/bbeh.py
opencompass/configs/summarizers/groups/bbh.py
opencompass/configs/summarizers/groups/calm.py
opencompass/configs/summarizers/groups/ceval.py
opencompass/configs/summarizers/groups/charm_reason.py
opencompass/configs/summarizers/groups/cibench.py
opencompass/configs/summarizers/groups/cmmlu.py
opencompass/configs/summarizers/groups/ds1000.py
opencompass/configs/summarizers/groups/flores.py
opencompass/configs/summarizers/groups/humanevalx.py
opencompass/configs/summarizers/groups/infinitebench.py
opencompass/configs/summarizers/groups/jigsaw_multilingual.py
opencompass/configs/summarizers/groups/korbench.py
opencompass/configs/summarizers/groups/lawbench.py
opencompass/configs/summarizers/groups/lcbench.py
opencompass/configs/summarizers/groups/leval.py
opencompass/configs/summarizers/groups/longbench.py
opencompass/configs/summarizers/groups/lveval.py
opencompass/configs/summarizers/groups/mathbench.py
opencompass/configs/summarizers/groups/mathbench_2024.py
opencompass/configs/summarizers/groups/mathbench_agent.py
opencompass/configs/summarizers/groups/mathbench_v1.py
opencompass/configs/summarizers/groups/mathbench_v1_2024.py
opencompass/configs/summarizers/groups/mathbench_v1_2024_lang.py
opencompass/configs/summarizers/groups/mgsm.py
opencompass/configs/summarizers/groups/mmlu.py
opencompass/configs/summarizers/groups/mmlu_cf.py
opencompass/configs/summarizers/groups/mmlu_pro.py
opencompass/configs/summarizers/groups/mmmlu.py
opencompass/configs/summarizers/groups/multipl_e.py
opencompass/configs/summarizers/groups/musr_average.py
opencompass/configs/summarizers/groups/plugineval.py
opencompass/configs/summarizers/groups/ruler.py
opencompass/configs/summarizers/groups/scibench.py
opencompass/configs/summarizers/groups/scicode.py
opencompass/configs/summarizers/groups/supergpqa.py
opencompass/configs/summarizers/groups/teval.py
opencompass/configs/summarizers/groups/tydiqa.py
opencompass/configs/summarizers/groups/xiezhi.py
opencompass/configs/summarizers/groups/legacy/cibench.py
opencompass/datasets/CARDBiomedBench.py
opencompass/datasets/ClinicBench.py
opencompass/datasets/Earth_Silver.py
opencompass/datasets/FinanceIQ.py
opencompass/datasets/GaokaoBench.py
opencompass/datasets/LCBench.py
opencompass/datasets/MMLUArabic.py
opencompass/datasets/MedCalc_Bench.py
opencompass/datasets/MedQA.py
opencompass/datasets/MedXpertQA.py
opencompass/datasets/Medbullets.py
opencompass/datasets/OlympiadBench.py
opencompass/datasets/OpenFinData.py
opencompass/datasets/ProteinLMBench.py
opencompass/datasets/PubMedQA.py
opencompass/datasets/QuALITY.py
opencompass/datasets/SciEval.py
opencompass/datasets/SciKnowEval.py
opencompass/datasets/ScienceQA.py
opencompass/datasets/__init__.py
opencompass/datasets/advglue.py
opencompass/datasets/afqmcd.py
opencompass/datasets/aime2024.py
opencompass/datasets/anli.py
opencompass/datasets/anthropics_evals.py
opencompass/datasets/apps.py
opencompass/datasets/arc.py
opencompass/datasets/arc_prize_public_evaluation.py
opencompass/datasets/ax.py
opencompass/datasets/base.py
opencompass/datasets/bbeh.py
opencompass/datasets/bbh.py
opencompass/datasets/benbench.py
opencompass/datasets/boolq.py
opencompass/datasets/bustum.py
opencompass/datasets/c3.py
opencompass/datasets/cb.py
opencompass/datasets/ceval.py
opencompass/datasets/charm.py
opencompass/datasets/chem_exam.py
opencompass/datasets/chembench.py
opencompass/datasets/chid.py
opencompass/datasets/chinese_simpleqa.py
opencompass/datasets/cibench.py
opencompass/datasets/circular.py
opencompass/datasets/civilcomments.py
opencompass/datasets/climaqa.py
opencompass/datasets/clozeTest_maxmin.py
opencompass/datasets/cluewsc.py
opencompass/datasets/cmb.py
opencompass/datasets/cmmlu.py
opencompass/datasets/cmnli.py
opencompass/datasets/cmo_fib.py
opencompass/datasets/cmrc.py
opencompass/datasets/commonsenseqa.py
opencompass/datasets/commonsenseqa_cn.py
opencompass/datasets/compassbench_obj.py
opencompass/datasets/copa.py
opencompass/datasets/crowspairs.py
opencompass/datasets/crowspairs_cn.py
opencompass/datasets/csl.py
opencompass/datasets/custom.py
opencompass/datasets/cvalues.py
opencompass/datasets/dingo.py
opencompass/datasets/drcd.py
opencompass/datasets/drop.py
opencompass/datasets/drop_simple_eval.py
opencompass/datasets/ds1000.py
opencompass/datasets/ds1000_interpreter.py
opencompass/datasets/eprstmt.py
opencompass/datasets/flores.py
opencompass/datasets/game24.py
opencompass/datasets/gaokao_math.py
opencompass/datasets/generic.py
opencompass/datasets/govrepcrs.py
opencompass/datasets/gpqa.py
opencompass/datasets/gsm8k.py
opencompass/datasets/gsm_hard.py
opencompass/datasets/hellaswag.py
opencompass/datasets/hle.py
opencompass/datasets/huggingface.py
opencompass/datasets/humaneval.py
opencompass/datasets/humaneval_multi.py
opencompass/datasets/humaneval_pro.py
opencompass/datasets/humanevalx.py
opencompass/datasets/hungarian_math.py
opencompass/datasets/inference_ppl.py
opencompass/datasets/internsandbox.py
opencompass/datasets/iwslt2017.py
opencompass/datasets/jigsawmultilingual.py
opencompass/datasets/jsonl.py
opencompass/datasets/kaoshi.py
opencompass/datasets/kcle.py
opencompass/datasets/lambada.py
opencompass/datasets/lcsts.py
opencompass/datasets/livestembench.py
opencompass/datasets/llm_compression.py
opencompass/datasets/lmeval.py
opencompass/datasets/longbenchv2.py
opencompass/datasets/mastermath2024v1.py
opencompass/datasets/math.py
opencompass/datasets/math401.py
opencompass/datasets/math_intern.py
opencompass/datasets/mathbench.py
opencompass/datasets/mbpp.py
opencompass/datasets/mbpp_pro.py
opencompass/datasets/medmcqa.py
opencompass/datasets/mgsm.py
opencompass/datasets/mmlu.py
opencompass/datasets/mmlu_cf.py
opencompass/datasets/mmlu_pro.py
opencompass/datasets/mmmlu.py
opencompass/datasets/multipl_e.py
opencompass/datasets/multirc.py
opencompass/datasets/narrativeqa.py
opencompass/datasets/natural_question.py
opencompass/datasets/natural_question_cn.py
opencompass/datasets/nejmaibench.py
opencompass/datasets/obqa.py
opencompass/datasets/olymmath.py
opencompass/datasets/omni_math.py
opencompass/datasets/physics.py
opencompass/datasets/piqa.py
opencompass/datasets/py150.py
opencompass/datasets/qasper.py
opencompass/datasets/qaspercut.py
opencompass/datasets/race.py
opencompass/datasets/rbench.py
opencompass/datasets/realtoxicprompts.py
opencompass/datasets/record.py
opencompass/datasets/rolebench.py
opencompass/datasets/s3eval.py
opencompass/datasets/safety.py
opencompass/datasets/scibench.py
opencompass/datasets/scicode.py
opencompass/datasets/simpleqa.py
opencompass/datasets/siqa.py
opencompass/datasets/smolinstruct.py
opencompass/datasets/squad20.py
opencompass/datasets/srbench.py
opencompass/datasets/storycloze.py
opencompass/datasets/strategyqa.py
opencompass/datasets/summedits.py
opencompass/datasets/summscreen.py
opencompass/datasets/svamp.py
opencompass/datasets/tabmwp.py
opencompass/datasets/taco.py
opencompass/datasets/tnews.py
opencompass/datasets/triviaqa.py
opencompass/datasets/triviaqarc.py
opencompass/datasets/truthfulqa.py
opencompass/datasets/tydiqa.py
opencompass/datasets/wic.py
opencompass/datasets/wikibench.py
opencompass/datasets/winograd.py
opencompass/datasets/winogrande.py
opencompass/datasets/wnli.py
opencompass/datasets/wsc.py
opencompass/datasets/xcopa.py
opencompass/datasets/xiezhi.py
opencompass/datasets/xlsum.py
opencompass/datasets/xsum.py
opencompass/datasets/IFEval/__init__.py
opencompass/datasets/IFEval/evaluation_main.py
opencompass/datasets/IFEval/ifeval.py
opencompass/datasets/IFEval/instructions.py
opencompass/datasets/IFEval/instructions_registry.py
opencompass/datasets/IFEval/instructions_util.py
opencompass/datasets/NPHardEval/__init__.py
opencompass/datasets/NPHardEval/cmp_GCP_D.py
opencompass/datasets/NPHardEval/cmp_KSP.py
opencompass/datasets/NPHardEval/cmp_TSP_D.py
opencompass/datasets/NPHardEval/hard_GCP.py
opencompass/datasets/NPHardEval/hard_MSP.py
opencompass/datasets/NPHardEval/hard_TSP.py
opencompass/datasets/NPHardEval/p_BSP.py
opencompass/datasets/NPHardEval/p_EDP.py
opencompass/datasets/NPHardEval/p_SPP.py
opencompass/datasets/NPHardEval/prompts.py
opencompass/datasets/NPHardEval/utils.py
opencompass/datasets/PMMEval/__init__.py
opencompass/datasets/PMMEval/flores.py
opencompass/datasets/PMMEval/humanevalxl.py
opencompass/datasets/PMMEval/mgsm.py
opencompass/datasets/PMMEval/mhellaswag.py
opencompass/datasets/PMMEval/mifeval.py
opencompass/datasets/PMMEval/mlogiqa.py
opencompass/datasets/PMMEval/mmmlu.py
opencompass/datasets/PMMEval/xnli.py
opencompass/datasets/PMMEval/mifeval_utils/__init__.py
opencompass/datasets/PMMEval/mifeval_utils/combination_checker.py
opencompass/datasets/PMMEval/mifeval_utils/detectable_content_checker.py
opencompass/datasets/PMMEval/mifeval_utils/detectable_format_checker.py
opencompass/datasets/PMMEval/mifeval_utils/keywords_checker.py
opencompass/datasets/PMMEval/mifeval_utils/length_constraints_checker.py
opencompass/datasets/PMMEval/mifeval_utils/punctuation_checker.py
opencompass/datasets/PMMEval/mifeval_utils/startend_checker.py
opencompass/datasets/TheoremQA/__init__.py
opencompass/datasets/TheoremQA/legacy.py
opencompass/datasets/TheoremQA/main.py
opencompass/datasets/TheoremQA/number_utils.py
opencompass/datasets/TheoremQA/utils.py
opencompass/datasets/agieval/__init__.py
opencompass/datasets/agieval/agieval.py
opencompass/datasets/agieval/constructions.py
opencompass/datasets/agieval/dataset_loader.py
opencompass/datasets/agieval/evaluation.py
opencompass/datasets/agieval/math_equivalence.py
opencompass/datasets/agieval/post_process.py
opencompass/datasets/agieval/utils.py
opencompass/datasets/babilong/__init__.py
opencompass/datasets/babilong/babilong.py
opencompass/datasets/babilong/babilong_utils.py
opencompass/datasets/babilong/prompts.py
opencompass/datasets/bigcodebench/__init__.py
opencompass/datasets/bigcodebench/bigcodebench.py
opencompass/datasets/bigcodebench/extractor.py
opencompass/datasets/calm/__init__.py
opencompass/datasets/calm/calm.py
opencompass/datasets/calm/data_processing/__init__.py
opencompass/datasets/calm/data_processing/generate_questions.py
opencompass/datasets/calm/data_processing/task_hiearchy.py
opencompass/datasets/calm/data_processing/prompt/AC-B_causal_judgement.py
opencompass/datasets/calm/data_processing/prompt/AR-B_CaLM-AR.py
opencompass/datasets/calm/data_processing/prompt/ATE.py
opencompass/datasets/calm/data_processing/prompt/BAS-B_backadj.py
opencompass/datasets/calm/data_processing/prompt/BAS-C_max-BAS.py
opencompass/datasets/calm/data_processing/prompt/BAS-C_min-BAS.py
opencompass/datasets/calm/data_processing/prompt/BAS-C_mix-BAS.py
opencompass/datasets/calm/data_processing/prompt/CA-B_FA.py
opencompass/datasets/calm/data_processing/prompt/CA-B_FP.py
opencompass/datasets/calm/data_processing/prompt/CB-B_collider-bias.py
opencompass/datasets/calm/data_processing/prompt/CDE.py
opencompass/datasets/calm/data_processing/prompt/CEG-O_E-CARE.py
opencompass/datasets/calm/data_processing/prompt/CEI-B.py
opencompass/datasets/calm/data_processing/prompt/CORR-B_correlation.py
opencompass/datasets/calm/data_processing/prompt/CR-B_det-counterfactual.py
opencompass/datasets/calm/data_processing/prompt/CR-C_CRASS.py
opencompass/datasets/calm/data_processing/prompt/EAE-B_exp-away.py
opencompass/datasets/calm/data_processing/prompt/ECI-B_CTB.py
opencompass/datasets/calm/data_processing/prompt/ECI-B_ESC.py
opencompass/datasets/calm/data_processing/prompt/ECI-B_MAVEN-ERE.py
opencompass/datasets/calm/data_processing/prompt/ETT.py
opencompass/datasets/calm/data_processing/prompt/FAS-C_FAS.py
opencompass/datasets/calm/data_processing/prompt/IV-C_CaLM-IV.py
opencompass/datasets/calm/data_processing/prompt/NDE.py
opencompass/datasets/calm/data_processing/prompt/NIE.py
opencompass/datasets/calm/data_processing/prompt/PCD-B_COPA.py
opencompass/datasets/calm/data_processing/prompt/PCD-B_E-CARE.py
opencompass/datasets/calm/data_processing/prompt/PCD-C_COPA.py
opencompass/datasets/calm/data_processing/prompt/PCD-C_E-CARE.py
opencompass/datasets/calm/data_processing/prompt/PN.py
opencompass/datasets/calm/data_processing/prompt/PS.py
opencompass/datasets/calm/evaluation/__init__.py
opencompass/datasets/calm/evaluation/core_metrics.py
opencompass/datasets/calm/evaluation/errors.py
opencompass/datasets/calm/evaluation/accuracy/choice.py
opencompass/datasets/calm/evaluation/accuracy/open-ended.py
opencompass/datasets/calm/evaluation/accuracy/prob.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/AC-B_causal_judgement.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/AR-B_CaLM-AR.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/AS.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/CA-B.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/CEI-B.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/CLADDER.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/CR-C_CRASS.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/ECI.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/Natural.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/PCD-B.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/PCD-C.py
opencompass/datasets/calm/evaluation/error/basic_adversarial/Probability.py
opencompass/datasets/calm/evaluation/labeling/AC-B_causal_judgement.py
opencompass/datasets/calm/evaluation/labeling/AR-B_CaLM-AR.py
opencompass/datasets/calm/evaluation/labeling/AS.py
opencompass/datasets/calm/evaluation/labeling/CA-B_FA.py
opencompass/datasets/calm/evaluation/labeling/CA-B_FP.py
opencompass/datasets/calm/evaluation/labeling/CEG-O_E-CARE.py
opencompass/datasets/calm/evaluation/labeling/CEI-B.py
opencompass/datasets/calm/evaluation/labeling/CLADDER.py
opencompass/datasets/calm/evaluation/labeling/CR-C_CRASS.py
opencompass/datasets/calm/evaluation/labeling/ECI.py
opencompass/datasets/calm/evaluation/labeling/Natural.py
opencompass/datasets/calm/evaluation/labeling/PCD-B.py
opencompass/datasets/calm/evaluation/labeling/PCD-C.py
opencompass/datasets/calm/evaluation/labeling/Probability.py
opencompass/datasets/calm/evaluation/labeling/common_answers.py
opencompass/datasets/calm/utils/__init__.py
opencompass/datasets/calm/utils/load_items.py
opencompass/datasets/codecompass/CodeCompass.py
opencompass/datasets/codecompass/__init__.py
opencompass/datasets/codecompass/codecompass_runner.py
opencompass/datasets/codecompass/evaluator.py
opencompass/datasets/codecompass/executor.py
opencompass/datasets/codecompass/metrics.py
opencompass/datasets/codecompass/utils.py
opencompass/datasets/eese/eese.py
opencompass/datasets/eese/eese_postprocessors.py
opencompass/datasets/eese/utils.py
opencompass/datasets/healthbench/healthbench.py
opencompass/datasets/healthbench/types.py
opencompass/datasets/healthbench/sampler/chat_completion_sampler.py
opencompass/datasets/infinitebench/__init__.py
opencompass/datasets/infinitebench/infinitebench_codedebug.py
opencompass/datasets/infinitebench/infinitebench_coderun.py
opencompass/datasets/infinitebench/infinitebench_endia.py
opencompass/datasets/infinitebench/infinitebench_enmc.py
opencompass/datasets/infinitebench/infinitebench_enqa.py
opencompass/datasets/infinitebench/infinitebench_ensum.py
opencompass/datasets/infinitebench/infinitebench_mathcalc.py
opencompass/datasets/infinitebench/infinitebench_mathfind.py
opencompass/datasets/infinitebench/infinitebench_retrievekv.py
opencompass/datasets/infinitebench/infinitebench_retrievenumber.py
opencompass/datasets/infinitebench/infinitebench_retrievepasskey.py
opencompass/datasets/infinitebench/infinitebench_zhqa.py
opencompass/datasets/infinitebench/utils.py
opencompass/datasets/judge/__init__.py
opencompass/datasets/judge/judgebench.py
opencompass/datasets/judge/judgerbenchv2.py
opencompass/datasets/judge/rewardbench.py
opencompass/datasets/judge/rmb.py
opencompass/datasets/korbench/__init__.py
opencompass/datasets/korbench/korbench.py
opencompass/datasets/korbench/korbench_utils.py
opencompass/datasets/korbench/korbench_dataset_config/__init__.py
opencompass/datasets/korbench/korbench_dataset_config/config.yaml
opencompass/datasets/korbench/korbench_dataset_config/config_wrapper.py
opencompass/datasets/korbench/korbench_dataset_config/prompt/0_shot.yaml
opencompass/datasets/korbench/korbench_dataset_config/prompt/3_shot.yaml
opencompass/datasets/korbench/korbench_dataset_config/prompt/__init__.py
opencompass/datasets/korbench/korbench_dataset_config/prompt/mixed.yaml
opencompass/datasets/korbench/korbench_dataset_config/prompt/self-correction.yaml
opencompass/datasets/korbench/korbench_dataset_config/prompt/trick.yaml
opencompass/datasets/lawbench/__init__.py
opencompass/datasets/lawbench/lawbench.py
opencompass/datasets/lawbench/evaluation_functions/__init__.py
opencompass/datasets/lawbench/evaluation_functions/cjft.py
opencompass/datasets/lawbench/evaluation_functions/flzx.py
opencompass/datasets/lawbench/evaluation_functions/ftcs.py
opencompass/datasets/lawbench/evaluation_functions/jdzy.py
opencompass/datasets/lawbench/evaluation_functions/jec_ac.py
opencompass/datasets/lawbench/evaluation_functions/jec_kd.py
opencompass/datasets/lawbench/evaluation_functions/jetq.py
opencompass/datasets/lawbench/evaluation_functions/lblj.py
opencompass/datasets/lawbench/evaluation_functions/ljp_accusation.py
opencompass/datasets/lawbench/evaluation_functions/ljp_article.py
opencompass/datasets/lawbench/evaluation_functions/ljp_imprison.py
opencompass/datasets/lawbench/evaluation_functions/sjjc.py
opencompass/datasets/lawbench/evaluation_functions/wbfl.py
opencompass/datasets/lawbench/evaluation_functions/wsjd.py
opencompass/datasets/lawbench/evaluation_functions/xxcq.py
opencompass/datasets/lawbench/evaluation_functions/ydlj.py
opencompass/datasets/lawbench/evaluation_functions/yqzy.py
opencompass/datasets/lawbench/evaluation_functions/zxfl.py
opencompass/datasets/lawbench/utils/__init__.py
opencompass/datasets/lawbench/utils/char_smi.py
opencompass/datasets/lawbench/utils/compare_m2_for_evaluation.py
opencompass/datasets/lawbench/utils/comprehension_scores.py
opencompass/datasets/lawbench/utils/function_utils.py
opencompass/datasets/lawbench/utils/parallel_to_m2.py
opencompass/datasets/lawbench/utils/rc_f1.py
opencompass/datasets/lawbench/utils/modules/__init__.py
opencompass/datasets/lawbench/utils/modules/alignment.py
opencompass/datasets/lawbench/utils/modules/annotator.py
opencompass/datasets/lawbench/utils/modules/classifier.py
opencompass/datasets/lawbench/utils/modules/merger.py
opencompass/datasets/lawbench/utils/modules/tokenization.py
opencompass/datasets/lawbench/utils/modules/tokenizer.py
opencompass/datasets/leval/__init__.py
opencompass/datasets/leval/evaluators.py
opencompass/datasets/leval/leval_coursera.py
opencompass/datasets/leval/leval_financial_qa.py
opencompass/datasets/leval/leval_gov_report_summ.py
opencompass/datasets/leval/leval_gsm100.py
opencompass/datasets/leval/leval_legal_contract_qa.py
opencompass/datasets/leval/leval_meeting_summ.py
opencompass/datasets/leval/leval_multidoc_qa.py
opencompass/datasets/leval/leval_narrattive_qa.py
opencompass/datasets/leval/leval_natural_question.py
opencompass/datasets/leval/leval_news_summ.py
opencompass/datasets/leval/leval_paper_assistant.py
opencompass/datasets/leval/leval_patent_summ.py
opencompass/datasets/leval/leval_quality.py
opencompass/datasets/leval/leval_review_summ.py
opencompass/datasets/leval/leval_scientific_qa.py
opencompass/datasets/leval/leval_topic_retrieval.py
opencompass/datasets/leval/leval_tpo.py
opencompass/datasets/leval/leval_tvshow_summ.py
opencompass/datasets/livecodebench/__init__.py
opencompass/datasets/livecodebench/evaluator.py
opencompass/datasets/livecodebench/execute_utils.py
opencompass/datasets/livecodebench/extract_utils.py
opencompass/datasets/livecodebench/livecodebench.py
opencompass/datasets/livecodebench/pass_k_utils.py
opencompass/datasets/livecodebench/prompts.py
opencompass/datasets/livecodebench/testing_util.py
opencompass/datasets/livemathbench/__init__.py
opencompass/datasets/livemathbench/livemathbench.py
opencompass/datasets/livemathbench/prompts.py
opencompass/datasets/livemathbench/utils.py
opencompass/datasets/livereasonbench/__init__.py
opencompass/datasets/livereasonbench/livereasonbench.py
opencompass/datasets/longbench/__init__.py
opencompass/datasets/longbench/evaluators.py
opencompass/datasets/longbench/longbench_2wikim_qa.py
opencompass/datasets/longbench/longbench_dureader.py
opencompass/datasets/longbench/longbench_gov_report.py
opencompass/datasets/longbench/longbench_hotpot_qa.py
opencompass/datasets/longbench/longbench_lcc.py
opencompass/datasets/longbench/longbench_lsht.py
opencompass/datasets/longbench/longbench_multi_news.py
opencompass/datasets/longbench/longbench_multifieldqa_en.py
opencompass/datasets/longbench/longbench_multifieldqa_zh.py
opencompass/datasets/longbench/longbench_musique.py
opencompass/datasets/longbench/longbench_narrative_qa.py
opencompass/datasets/longbench/longbench_passage_count.py
opencompass/datasets/longbench/longbench_passage_retrieval_en.py
opencompass/datasets/longbench/longbench_passage_retrieval_zh.py
opencompass/datasets/longbench/longbench_qasper.py
opencompass/datasets/longbench/longbench_qmsum.py
opencompass/datasets/longbench/longbench_repobench.py
opencompass/datasets/longbench/longbench_samsum.py
opencompass/datasets/longbench/longbench_trec.py
opencompass/datasets/longbench/longbench_trivia_qa.py
opencompass/datasets/longbench/longbench_vcsum.py
opencompass/datasets/lveval/__init__.py
opencompass/datasets/lveval/evaluators.py
opencompass/datasets/lveval/lveval_cmrc_mixup.py
opencompass/datasets/lveval/lveval_dureader_mixup.py
opencompass/datasets/lveval/lveval_factrecall_en.py
opencompass/datasets/lveval/lveval_factrecall_zh.py
opencompass/datasets/lveval/lveval_hotpotwikiqa_mixup.py
opencompass/datasets/lveval/lveval_lic_mixup.py
opencompass/datasets/lveval/lveval_loogle_CR_mixup.py
opencompass/datasets/lveval/lveval_loogle_MIR_mixup.py
opencompass/datasets/lveval/lveval_loogle_SD_mixup.py
opencompass/datasets/lveval/lveval_multifieldqa_en_mixup.py
opencompass/datasets/lveval/lveval_multifieldqa_zh_mixup.py
opencompass/datasets/matbench/__init__.py
opencompass/datasets/matbench/matbench.py
opencompass/datasets/matbench/post_process.py
opencompass/datasets/medbench/__init__.py
opencompass/datasets/medbench/constructions.py
opencompass/datasets/medbench/dataset_loader.py
opencompass/datasets/medbench/evaluation.py
opencompass/datasets/medbench/math_equivalence.py
opencompass/datasets/medbench/medbench.py
opencompass/datasets/medbench/post_process.py
opencompass/datasets/medbench/utils.py
opencompass/datasets/musr/__init__.py
opencompass/datasets/musr/murder_mystery_solved_ex.py
opencompass/datasets/musr/musr.py
opencompass/datasets/musr/object_placements_solved_ex.py
opencompass/datasets/musr/team_allocation_solved_ex.py
opencompass/datasets/musr/tree.py
opencompass/datasets/needlebench/__init__.py
opencompass/datasets/needlebench/atc.py
opencompass/datasets/needlebench/atc_choice.py
opencompass/datasets/needlebench/multi.py
opencompass/datasets/needlebench/origin.py
opencompass/datasets/needlebench/parallel.py
opencompass/datasets/needlebench_v2/__init__.py
opencompass/datasets/needlebench_v2/atc.py
opencompass/datasets/needlebench_v2/atc_elder_only.py
opencompass/datasets/needlebench_v2/multi.py
opencompass/datasets/needlebench_v2/origin.py
opencompass/datasets/needlebench_v2/parallel.py
opencompass/datasets/phybench/EED.py
opencompass/datasets/phybench/__init__.py
opencompass/datasets/phybench/box_extract.py
opencompass/datasets/phybench/extended_zss.py
opencompass/datasets/phybench/latex_pre_process.py
opencompass/datasets/phybench/phybench.py
opencompass/datasets/reasonbench/ReasonBenchDataset.py
opencompass/datasets/reasonbench/__init__.py
opencompass/datasets/ruler/__init__.py
opencompass/datasets/ruler/ruler_cwe.py
opencompass/datasets/ruler/ruler_fwe.py
opencompass/datasets/ruler/ruler_niah.py
opencompass/datasets/ruler/ruler_qa.py
opencompass/datasets/ruler/ruler_vt.py
opencompass/datasets/sage/dataset_loader.py
opencompass/datasets/sage/evaluation.py
opencompass/datasets/sage/prompt.py
opencompass/datasets/subjective/__init__.py
opencompass/datasets/subjective/alignbench.py
opencompass/datasets/subjective/alpacaeval.py
opencompass/datasets/subjective/arena_hard.py
opencompass/datasets/subjective/commonbench.py
opencompass/datasets/subjective/compass_arena.py
opencompass/datasets/subjective/compass_arena_subjective_bench.py
opencompass/datasets/subjective/compassbench.py
opencompass/datasets/subjective/compassbench_checklist.py
opencompass/datasets/subjective/compassbench_control_length_bias.py
opencompass/datasets/subjective/corev2.py
opencompass/datasets/subjective/creationbench.py
opencompass/datasets/subjective/flames.py
opencompass/datasets/subjective/fofo.py
opencompass/datasets/subjective/followbench.py
opencompass/datasets/subjective/hellobench.py
opencompass/datasets/subjective/judgerbench.py
opencompass/datasets/subjective/mtbench.py
opencompass/datasets/subjective/mtbench101.py
opencompass/datasets/subjective/multiround.py
opencompass/datasets/subjective/subjective_cmp.py
opencompass/datasets/subjective/utils.py
opencompass/datasets/subjective/wildbench.py
opencompass/datasets/subjective/writingbench.py
opencompass/datasets/supergpqa/__init__.py
opencompass/datasets/supergpqa/supergpqa.py
opencompass/datasets/supergpqa/supergpqa_eval.py
opencompass/datasets/supergpqa/supergpqa_utils.py
opencompass/datasets/supergpqa/supergpqa_dataset_config/config_default.yaml
opencompass/datasets/supergpqa/supergpqa_dataset_config/config_reasoning_models.yaml
opencompass/datasets/supergpqa/supergpqa_dataset_config/config_wrapper.py
opencompass/datasets/supergpqa/supergpqa_dataset_config/prompt/five-shot.yaml
opencompass/datasets/supergpqa/supergpqa_dataset_config/prompt/robustness-exp.yaml
opencompass/datasets/supergpqa/supergpqa_dataset_config/prompt/zero-shot-with-subfield.yaml
opencompass/datasets/supergpqa/supergpqa_dataset_config/prompt/zero-shot.yaml
opencompass/datasets/teval/__init__.py
opencompass/datasets/teval/schema.py
opencompass/datasets/teval/evaluators/__init__.py
opencompass/datasets/teval/evaluators/instruct_evaluator.py
opencompass/datasets/teval/evaluators/planning_evaluator.py
opencompass/datasets/teval/evaluators/reason_retrieve_understand_evaluator.py
opencompass/datasets/teval/evaluators/review_evaluator.py
opencompass/datasets/teval/utils/__init__.py
opencompass/datasets/teval/utils/convert_results.py
opencompass/datasets/teval/utils/format_load.py
opencompass/datasets/teval/utils/meta_template.py
opencompass/datasets/teval/utils/template.py
opencompass/evaluator/__init__.py
opencompass/evaluator/cascade_evaluator.py
opencompass/evaluator/generic_llm_evaluator.py
opencompass/evaluator/math_evaluator.py
opencompass/metrics/__init__.py
opencompass/metrics/dump_results.py
opencompass/metrics/mme_score.py
opencompass/metrics/seedbench.py
opencompass/models/__init__.py
opencompass/models/accessory.py
opencompass/models/ai360_api.py
opencompass/models/alaya.py
opencompass/models/baichuan_api.py
opencompass/models/baidu_api.py
opencompass/models/bailing_api_oc.py
opencompass/models/base.py
opencompass/models/base_api.py
opencompass/models/bluelm_api.py
opencompass/models/bytedance_api.py
opencompass/models/claude_allesapin.py
opencompass/models/claude_sdk_api.py
opencompass/models/deepseek_api.py
opencompass/models/doubao.py
opencompass/models/doubao_api.py
opencompass/models/gemini_api.py
opencompass/models/glm.py
opencompass/models/huggingface.py
opencompass/models/huggingface_above_v4_33.py
opencompass/models/hunyuan_api.py
opencompass/models/intern_model.py
opencompass/models/interntrain.py
opencompass/models/krgpt_api.py
opencompass/models/lagent.py
opencompass/models/langchain.py
opencompass/models/lightllm_api.py
opencompass/models/llama2.py
opencompass/models/minimax_api.py
opencompass/models/mistral_api.py
opencompass/models/mixtral.py
opencompass/models/modelscope.py
opencompass/models/moonshot_api.py
opencompass/models/nanbeige_api.py
opencompass/models/openai_api.py
opencompass/models/openai_streaming.py
opencompass/models/pangu_api.py
opencompass/models/qwen_api.py
opencompass/models/rendu_api.py
opencompass/models/sensetime_api.py
opencompass/models/stepfun_api.py
opencompass/models/turbomind.py
opencompass/models/turbomind_api.py
opencompass/models/turbomind_with_tf_above_v4_33.py
opencompass/models/unigpt_api.py
opencompass/models/vllm.py
opencompass/models/vllm_with_tf_above_v4_33.py
opencompass/models/xunfei_api.py
opencompass/models/yayi_api.py
opencompass/models/yi_api.py
opencompass/models/zhipuai_api.py
opencompass/models/zhipuai_v2_api.py
opencompass/models/claude_api/__init__.py
opencompass/models/claude_api/claude_api.py
opencompass/models/claude_api/postprocessors.py
opencompass/openicl/__init__.py
opencompass/openicl/icl_dataset_reader.py
opencompass/openicl/icl_prompt_template.py
opencompass/openicl/icl_evaluator/__init__.py
opencompass/openicl/icl_evaluator/code_evaluator.py
opencompass/openicl/icl_evaluator/icl_agent_evaluator.py
opencompass/openicl/icl_evaluator/icl_aucroc_evaluator.py
opencompass/openicl/icl_evaluator/icl_base_evaluator.py
opencompass/openicl/icl_evaluator/icl_bpc_evaluator.py
opencompass/openicl/icl_evaluator/icl_circular_evaluator.py
opencompass/openicl/icl_evaluator/icl_em_evaluator.py
opencompass/openicl/icl_evaluator/icl_hf_evaluator.py
opencompass/openicl/icl_evaluator/icl_jieba_rouge_evaluator.py
opencompass/openicl/icl_evaluator/icl_judge_evaluator.py
opencompass/openicl/icl_evaluator/icl_korbench_evaluator.py
opencompass/openicl/icl_evaluator/icl_misc_evaluator.py
opencompass/openicl/icl_evaluator/icl_plugin_evaluator.py
opencompass/openicl/icl_evaluator/icl_toxic_evaluator.py
opencompass/openicl/icl_evaluator/lm_evaluator.py
opencompass/openicl/icl_evaluator/hf_metrics/accuracy.py
opencompass/openicl/icl_evaluator/hf_metrics/rouge.py
opencompass/openicl/icl_evaluator/hf_metrics/sacrebleu.py
opencompass/openicl/icl_evaluator/hf_metrics/squad.py
opencompass/openicl/icl_inferencer/__init__.py
opencompass/openicl/icl_inferencer/icl_agent_inferencer.py
opencompass/openicl/icl_inferencer/icl_attack_inferencer.py
opencompass/openicl/icl_inferencer/icl_base_inferencer.py
opencompass/openicl/icl_inferencer/icl_chat_inferencer.py
opencompass/openicl/icl_inferencer/icl_clp_inferencer.py
opencompass/openicl/icl_inferencer/icl_gen_inferencer.py
opencompass/openicl/icl_inferencer/icl_inference_ppl_only_inferencer.py
opencompass/openicl/icl_inferencer/icl_ll_inferencer.py
opencompass/openicl/icl_inferencer/icl_mink_percent_inferencer.py
opencompass/openicl/icl_inferencer/icl_ppl_inferencer.py
opencompass/openicl/icl_inferencer/icl_ppl_only_inferencer.py
opencompass/openicl/icl_inferencer/icl_sc_inferencer.py
opencompass/openicl/icl_inferencer/icl_sw_ce_loss_inferencer.py
opencompass/openicl/icl_inferencer/icl_tot_inferencer.py
opencompass/openicl/icl_retriever/__init__.py
opencompass/openicl/icl_retriever/icl_base_retriever.py
opencompass/openicl/icl_retriever/icl_bm25_retriever.py
opencompass/openicl/icl_retriever/icl_dpp_retriever.py
opencompass/openicl/icl_retriever/icl_fix_k_retriever.py
opencompass/openicl/icl_retriever/icl_mdl_retriever.py
opencompass/openicl/icl_retriever/icl_random_retriever.py
opencompass/openicl/icl_retriever/icl_sliding_k_retriever.py
opencompass/openicl/icl_retriever/icl_topk_retriever.py
opencompass/openicl/icl_retriever/icl_votek_retriever.py
opencompass/openicl/icl_retriever/icl_zero_retriever.py
opencompass/openicl/utils/__init__.py
opencompass/openicl/utils/logging.py
opencompass/partitioners/__init__.py
opencompass/partitioners/base.py
opencompass/partitioners/naive.py
opencompass/partitioners/num_worker.py
opencompass/partitioners/size.py
opencompass/partitioners/sub_naive.py
opencompass/partitioners/sub_num_worker.py
opencompass/partitioners/sub_size.py
opencompass/runners/__init__.py
opencompass/runners/base.py
opencompass/runners/dlc.py
opencompass/runners/local.py
opencompass/runners/local_api.py
opencompass/runners/rjob.py
opencompass/runners/slurm.py
opencompass/runners/slurm_sequential.py
opencompass/runners/volc.py
opencompass/summarizers/__init__.py
opencompass/summarizers/circular.py
opencompass/summarizers/default.py
opencompass/summarizers/default_subjective.py
opencompass/summarizers/llm_compression.py
opencompass/summarizers/multi_faceted.py
opencompass/summarizers/multi_model.py
opencompass/summarizers/needlebench.py
opencompass/summarizers/summarizer_pretrain.py
opencompass/summarizers/subjective/__init__.py
opencompass/summarizers/subjective/alignmentbench.py
opencompass/summarizers/subjective/all_obj.py
opencompass/summarizers/subjective/alpacaeval.py
opencompass/summarizers/subjective/arenahard.py
opencompass/summarizers/subjective/charm.py
opencompass/summarizers/subjective/common_summarizer.py
opencompass/summarizers/subjective/compass_arena.py
opencompass/summarizers/subjective/compass_arena_bradley_terry.py
opencompass/summarizers/subjective/compassbench.py
opencompass/summarizers/subjective/compassbench_v13.py
opencompass/summarizers/subjective/corev2.py
opencompass/summarizers/subjective/creationbench.py
opencompass/summarizers/subjective/flames.py
opencompass/summarizers/subjective/fofo.py
opencompass/summarizers/subjective/followbench.py
opencompass/summarizers/subjective/mtbench.py
opencompass/summarizers/subjective/mtbench101.py
opencompass/summarizers/subjective/multiround.py
opencompass/summarizers/subjective/qacompassbench.py
opencompass/summarizers/subjective/subjective.py
opencompass/summarizers/subjective/subjective_post_process.py
opencompass/summarizers/subjective/utils.py
opencompass/summarizers/subjective/wildbench.py
opencompass/tasks/__init__.py
opencompass/tasks/base.py
opencompass/tasks/llm_eval.py
opencompass/tasks/openicl_attack.py
opencompass/tasks/openicl_eval.py
opencompass/tasks/openicl_infer.py
opencompass/tasks/subjective_eval.py
opencompass/utils/__init__.py
opencompass/utils/abbr.py
opencompass/utils/auxiliary.py
opencompass/utils/build.py
opencompass/utils/collect_env.py
opencompass/utils/datasets.py
opencompass/utils/datasets_info.py
opencompass/utils/dependency.py
opencompass/utils/dict_postprocessors.py
opencompass/utils/file.py
opencompass/utils/fileio.py
opencompass/utils/lark.py
opencompass/utils/logging.py
opencompass/utils/menu.py
opencompass/utils/network.py
opencompass/utils/prompt.py
opencompass/utils/result_station.py
opencompass/utils/run.py
opencompass/utils/text_postprocessors.py
opencompass/utils/types.py