diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 55eb17ea..c40d59cf 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -20,7 +20,7 @@ exclude: | ) repos: - repo: https://github.com/PyCQA/flake8 - rev: 5.0.4 + rev: 7.2.0 hooks: - id: flake8 exclude: | @@ -29,7 +29,7 @@ repos: examples/ ) - repo: https://github.com/PyCQA/isort - rev: 5.11.5 + rev: 6.0.1 hooks: - id: isort exclude: | @@ -47,7 +47,7 @@ repos: examples/ ) - repo: https://github.com/codespell-project/codespell - rev: v2.2.1 + rev: v2.4.1 hooks: - id: codespell exclude: | @@ -58,7 +58,7 @@ repos: examples/ ) - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.3.0 + rev: v5.0.0 hooks: - id: trailing-whitespace exclude: | @@ -81,7 +81,7 @@ repos: - id: mixed-line-ending args: ["--fix=lf"] - repo: https://github.com/executablebooks/mdformat - rev: 0.7.9 + rev: 0.7.22 hooks: - id: mdformat args: ["--number", "--table-width", "200"] diff --git a/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_gen.py b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_gen.py new file mode 100644 index 00000000..5381abcf --- /dev/null +++ b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_gen.py @@ -0,0 +1,61 @@ +from opencompass.openicl.icl_prompt_template import PromptTemplate +from opencompass.openicl.icl_retriever import FixKRetriever +from opencompass.openicl.icl_inferencer import GenInferencer +from opencompass.openicl.icl_evaluator import AccwithDetailsEvaluator +from opencompass.utils.text_postprocessors import first_option_postprocess +from opencompass.datasets import SciEvalDataset # 你自己实现的类 + +# 只评测 biology + multiple-choice 的 test split +_hint = ('Given a question and four options, please select the right answer. ' + "Your answer should be 'A', 'B', 'C' or 'D'.") + +scieval_reader_cfg = dict( + input_columns=['input', 'A', 'B', 'C', 'D'], + output_column='target', + train_split='test', +) + +scieval_infer_cfg = dict( + ice_template=dict( + type=PromptTemplate, + template=dict(round=[ + dict( + role='HUMAN', + prompt=f'{_hint}\nQuestion: {{input}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nAnswer: ' + ), + dict(role='BOT', prompt='{target}\n') + ]), + ), + prompt_template=dict( + type=PromptTemplate, + template=dict( + begin='', + round=[ + dict( + role='HUMAN', + prompt=f'{_hint}\nQuestion: {{input}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nAnswer: ' + ), + ], + ), + ice_token='', + ), + retriever=dict(type=FixKRetriever, fix_id_list=[0, 1, 2, 3, 4]), + inferencer=dict(type=GenInferencer), +) + +scieval_eval_cfg = dict( + evaluator=dict(type=AccwithDetailsEvaluator), + pred_postprocessor=dict(type=first_option_postprocess, options='ABCD'), +) + +scieval_datasets = [ + dict( + abbr='scieval_biology', + type=SciEvalDataset, + path='OpenDFM/SciEval', + name='default', + reader_cfg=scieval_reader_cfg, + infer_cfg=scieval_infer_cfg, + eval_cfg=scieval_eval_cfg, + ) +] diff --git a/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_llmjudge_gen.py b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_llmjudge_gen.py new file mode 100644 index 00000000..26af5cd3 --- /dev/null +++ b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_llmjudge_gen.py @@ -0,0 +1,125 @@ +# SciEval_lifescience_llmjudge_gen.py + +from mmengine.config import read_base +from opencompass.openicl.icl_prompt_template import PromptTemplate +from opencompass.openicl.icl_retriever import ZeroRetriever +from opencompass.openicl.icl_inferencer import GenInferencer +from opencompass.utils.text_postprocessors import match_answer_pattern +from opencompass.evaluator import GenericLLMEvaluator +from opencompass.datasets import generic_llmjudge_postprocess +from opencompass.datasets import SciEvalDataset + +with read_base(): + from .SciEval_lifescience_sets import SciEval_lifescience_subsets + +QUERY_TEMPLATE = """ +Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. + +{input} + +A) {A} +B) {B} +C) {C} +D) {D} +""".strip() + +GRADER_TEMPLATE = """ +Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly. + +Here are some evaluation criteria: +1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct. +2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question. +3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct. +4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct. + +Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of: +A: CORRECT +B: INCORRECT +Just return the letters "A" or "B", with no text around it. + +Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer. + +: {input} +A) {A} +B) {B} +C) {C} +D) {D} + + +: +{target} + + +: +{prediction} + + +Judging the correctness of candidates' answers: +""".strip() + +scieval_reader_cfg = dict( + input_columns=['input', 'A', 'B', 'C', 'D'], + output_column='target', + train_split='test', +) + +scieval_datasets = [] +for name in SciEval_lifescience_subsets: + scieval_infer_cfg = dict( + prompt_template=dict( + type=PromptTemplate, + template=dict( + round=[ + dict(role='HUMAN', prompt=QUERY_TEMPLATE), + ] + ) + ), + retriever=dict(type=ZeroRetriever), + inferencer=dict(type=GenInferencer), + ) + + scieval_eval_cfg = dict( + evaluator=dict( + type=GenericLLMEvaluator, + prompt_template=dict( + type=PromptTemplate, + template=dict( + begin=[ + dict( + role='SYSTEM', + fallback_role='HUMAN', + prompt=( + 'You are a helpful assistant who evaluates the correctness ' + "and quality of models' outputs." + ), + ) + ], + round=[ + dict(role='HUMAN', prompt=GRADER_TEMPLATE), + ], + ), + ), + dataset_cfg=dict( + type=SciEvalDataset, + path='OpenDFM/SciEval', + name='default', + reader_cfg=scieval_reader_cfg, + ), + judge_cfg=dict(), + dict_postprocessor=dict(type=generic_llmjudge_postprocess), + ), + pred_role='BOT', + ) + + scieval_datasets.append( + dict( + abbr=f'scieval_lifescience_{name}_llmjudge', + type=SciEvalDataset, + path='OpenDFM/SciEval', + name='default', + reader_cfg=scieval_reader_cfg, + infer_cfg=scieval_infer_cfg, + eval_cfg=scieval_eval_cfg, + mode='singlescore', + ) + ) diff --git a/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_sets.py b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_sets.py new file mode 100644 index 00000000..8d0a0a83 --- /dev/null +++ b/opencompass/configs/datasets/SciEval_lifscience/SciEval_lifescience_sets.py @@ -0,0 +1,3 @@ +SciEval_lifescience_subsets = [ + 'biology', # 大学生物学 +] diff --git a/opencompass/configs/datasets/mmlu_lifescience/README.md b/opencompass/configs/datasets/mmlu_lifescience/README.md new file mode 100644 index 00000000..eaa2181e --- /dev/null +++ b/opencompass/configs/datasets/mmlu_lifescience/README.md @@ -0,0 +1,368 @@ +# MMLU + +```bash +python3 run.py --models hf_internlm2_7b --datasets mmlu_ppl_ac766d --debug +python3 run.py --models hf_internlm2_chat_7b --datasets mmlu_gen_4d595a --debug +``` + +## Base Models + +| model | mmlu | mmlu-stem | mmlu-social-science | mmlu-humanities | mmlu-other | +|:------------------------:|-------:|------------:|----------------------:|------------------:|-------------:| +| llama-7b-turbomind | 35.66 | 31.22 | 37.70 | 38.90 | 37.01 | +| llama-13b-turbomind | 47.76 | 37.68 | 55.36 | 52.43 | 50.83 | +| llama-30b-turbomind | 58.55 | 46.95 | 67.35 | 65.13 | 60.78 | +| llama-65b-turbomind | 63.78 | 52.35 | 73.68 | 70.84 | 64.29 | +| llama-2-7b-turbomind | 46.78 | 37.81 | 52.11 | 51.69 | 50.04 | +| llama-2-13b-turbomind | 55.76 | 44.61 | 63.86 | 62.97 | 57.35 | +| llama-2-70b-turbomind | 69.87 | 58.30 | 79.86 | 75.84 | 71.58 | +| llama-3-8b-turbomind | 66.43 | 55.95 | 76.11 | 70.29 | 68.96 | +| llama-3-70b-turbomind | 79.35 | 70.66 | 87.54 | 83.43 | 80.42 | +| internlm2-1.8b-turbomind | 45.99 | 39.63 | 51.02 | 48.65 | 47.96 | +| internlm2-7b-turbomind | 65.84 | 56.48 | 74.43 | 69.68 | 67.75 | +| internlm2-20b-turbomind | 67.58 | 59.01 | 76.04 | 71.20 | 68.69 | +| qwen-1.8b-turbomind | 46.61 | 38.91 | 51.35 | 49.57 | 50.51 | +| qwen-7b-turbomind | 59.75 | 50.16 | 67.98 | 63.48 | 62.44 | +| qwen-14b-turbomind | 67.85 | 59.13 | 76.18 | 71.62 | 69.12 | +| qwen-72b-turbomind | 77.36 | 68.70 | 85.28 | 80.60 | 79.45 | +| qwen1.5-0.5b-hf | 39.98 | 33.96 | 45.08 | 41.59 | 42.48 | +| qwen1.5-1.8b-hf | 47.14 | 39.47 | 52.70 | 49.01 | 51.33 | +| qwen1.5-4b-hf | 57.03 | 47.80 | 64.86 | 60.10 | 60.20 | +| qwen1.5-7b-hf | 62.15 | 53.22 | 70.25 | 65.62 | 64.26 | +| qwen1.5-14b-hf | 69.10 | 61.46 | 77.57 | 71.25 | 70.29 | +| qwen1.5-32b-hf | 73.88 | 65.60 | 81.41 | 77.10 | 75.79 | +| qwen1.5-72b-hf | 77.02 | 69.00 | 84.55 | 80.60 | 78.21 | +| qwen1.5-moe-a2-7b-hf | 62.09 | 53.27 | 70.74 | 63.80 | 65.28 | +| mistral-7b-v0.1-hf | 64.04 | 53.21 | 73.65 | 68.04 | 67.00 | +| mistral-7b-v0.2-hf | 63.85 | 53.21 | 72.17 | 68.40 | 67.15 | +| mixtral-8x7b-v0.1-hf | 71.80 | 61.70 | 81.03 | 75.51 | 74.35 | +| mixtral-8x22b-v0.1-hf | 77.67 | 68.94 | 86.81 | 81.23 | 78.43 | +| yi-6b-hf | 64.08 | 52.61 | 74.10 | 68.58 | 67.11 | +| yi-34b-hf | 76.26 | 66.73 | 83.74 | 81.78 | 77.77 | +| deepseek-7b-base-hf | 49.22 | 40.17 | 56.73 | 53.46 | 51.26 | +| deepseek-67b-base-hf | 71.95 | 60.57 | 81.69 | 77.11 | 74.42 | + +### Details + +| model | college_biology | college_chemistry | college_computer_science | college_mathematics | college_physics | electrical_engineering | astronomy | anatomy | abstract_algebra | machine_learning | clinical_knowledge | global_facts | +|:------------------------:|------------------:|--------------------:|---------------------------:|----------------------:|------------------:|-------------------------:|------------:|----------:|-------------------:|-------------------:|---------------------:|---------------:| +| llama-7b-turbomind | 37.50 | 30.00 | 30.00 | 33.00 | 23.53 | 23.45 | 34.87 | 37.78 | 25.00 | 27.68 | 34.34 | 31.00 | +| llama-13b-turbomind | 46.53 | 30.00 | 42.00 | 36.00 | 18.63 | 42.76 | 46.71 | 46.67 | 30.00 | 32.14 | 45.66 | 37.00 | +| llama-30b-turbomind | 59.03 | 45.00 | 47.00 | 35.00 | 26.47 | 53.10 | 61.18 | 51.85 | 37.00 | 41.07 | 57.36 | 38.00 | +| llama-65b-turbomind | 68.75 | 49.00 | 47.00 | 37.00 | 35.29 | 55.17 | 73.03 | 57.78 | 30.00 | 48.21 | 66.04 | 38.00 | +| llama-2-7b-turbomind | 46.53 | 34.00 | 33.00 | 34.00 | 22.55 | 47.59 | 40.13 | 47.41 | 29.00 | 38.39 | 46.42 | 32.00 | +| llama-2-13b-turbomind | 59.03 | 44.00 | 48.00 | 29.00 | 26.47 | 50.34 | 53.29 | 49.63 | 35.00 | 28.57 | 60.00 | 32.00 | +| llama-2-70b-turbomind | 84.72 | 51.00 | 60.00 | 39.00 | 37.25 | 65.52 | 81.58 | 63.70 | 32.00 | 52.68 | 72.08 | 46.00 | +| llama-3-8b-turbomind | 77.08 | 46.00 | 51.00 | 31.00 | 51.96 | 62.76 | 67.11 | 68.15 | 34.00 | 52.68 | 74.72 | 35.00 | +| llama-3-70b-turbomind | 93.75 | 62.00 | 72.00 | 52.00 | 50.98 | 74.48 | 92.11 | 79.26 | 48.00 | 63.39 | 86.42 | 49.00 | +| internlm2-1.8b-turbomind | 38.89 | 37.00 | 44.00 | 35.00 | 30.39 | 49.66 | 50.66 | 44.44 | 25.00 | 35.71 | 51.32 | 32.00 | +| internlm2-7b-turbomind | 77.08 | 48.00 | 64.00 | 33.00 | 47.06 | 63.45 | 73.68 | 57.78 | 37.00 | 45.54 | 69.81 | 35.00 | +| internlm2-20b-turbomind | 83.33 | 51.00 | 61.00 | 36.00 | 45.10 | 64.83 | 75.00 | 59.26 | 39.00 | 53.57 | 73.58 | 32.00 | +| qwen-1.8b-turbomind | 42.36 | 36.00 | 39.00 | 34.00 | 27.45 | 51.03 | 50.66 | 42.96 | 31.00 | 31.25 | 53.21 | 28.00 | +| qwen-7b-turbomind | 67.36 | 48.00 | 53.00 | 28.00 | 39.22 | 59.31 | 63.82 | 49.63 | 34.00 | 38.39 | 63.02 | 37.00 | +| qwen-14b-turbomind | 78.47 | 51.00 | 62.00 | 42.00 | 49.02 | 65.52 | 71.05 | 60.00 | 37.00 | 58.93 | 71.32 | 40.00 | +| qwen-72b-turbomind | 93.75 | 56.00 | 66.00 | 56.00 | 50.98 | 80.69 | 85.53 | 73.33 | 41.00 | 62.50 | 83.77 | 54.00 | +| qwen1.5-0.5b-hf | 38.89 | 25.00 | 38.00 | 32.00 | 25.49 | 45.52 | 44.74 | 33.33 | 30.00 | 39.29 | 38.11 | 39.00 | +| qwen1.5-1.8b-hf | 43.75 | 34.00 | 45.00 | 38.00 | 28.43 | 47.59 | 47.37 | 40.74 | 32.00 | 31.25 | 53.96 | 37.00 | +| qwen1.5-4b-hf | 50.00 | 46.00 | 41.00 | 45.00 | 31.37 | 53.10 | 61.18 | 51.85 | 35.00 | 44.64 | 60.38 | 37.00 | +| qwen1.5-7b-hf | 66.67 | 48.00 | 55.00 | 37.00 | 41.18 | 60.69 | 65.79 | 52.59 | 39.00 | 41.07 | 68.68 | 43.00 | +| qwen1.5-14b-hf | 75.69 | 49.00 | 58.00 | 49.00 | 49.02 | 71.72 | 73.03 | 65.93 | 39.00 | 52.68 | 73.96 | 49.00 | +| qwen1.5-32b-hf | 85.42 | 53.00 | 59.00 | 51.00 | 53.92 | 72.41 | 82.24 | 63.70 | 43.00 | 58.04 | 78.11 | 50.00 | +| qwen1.5-72b-hf | 90.97 | 54.00 | 65.00 | 57.00 | 52.94 | 80.00 | 87.50 | 73.33 | 43.00 | 64.29 | 81.89 | 50.00 | +| qwen1.5-moe-a2-7b-hf | 62.50 | 44.00 | 54.00 | 41.00 | 49.02 | 58.62 | 69.74 | 57.78 | 37.00 | 38.39 | 66.79 | 38.00 | +| mistral-7b-v0.1-hf | 72.92 | 50.00 | 51.00 | 40.00 | 39.22 | 57.93 | 65.79 | 62.96 | 29.00 | 49.11 | 69.43 | 36.00 | +| mistral-7b-v0.2-hf | 71.53 | 49.00 | 53.00 | 40.00 | 36.27 | 57.24 | 64.47 | 60.00 | 29.00 | 53.57 | 67.92 | 39.00 | +| mixtral-8x7b-v0.1-hf | 85.42 | 54.00 | 62.00 | 43.00 | 46.08 | 68.97 | 82.89 | 70.37 | 37.00 | 56.25 | 79.25 | 51.00 | +| mixtral-8x22b-v0.1-hf | 89.58 | 56.00 | 69.00 | 48.00 | 52.94 | 76.55 | 86.18 | 77.04 | 53.00 | 62.50 | 82.26 | 56.00 | +| yi-6b-hf | 66.67 | 43.00 | 51.00 | 39.00 | 35.29 | 64.83 | 65.79 | 60.00 | 29.00 | 41.96 | 66.79 | 46.00 | +| yi-34b-hf | 88.89 | 52.00 | 66.00 | 44.00 | 48.04 | 80.00 | 89.47 | 74.81 | 44.00 | 58.04 | 78.87 | 52.00 | +| deepseek-7b-base-hf | 52.08 | 29.00 | 44.00 | 40.00 | 31.37 | 44.83 | 51.97 | 40.74 | 27.00 | 32.14 | 53.58 | 31.00 | +| deepseek-67b-base-hf | 84.72 | 52.00 | 62.00 | 42.00 | 42.16 | 70.34 | 80.92 | 65.19 | 39.00 | 50.00 | 78.11 | 42.00 | + +| model | management | nutrition | marketing | professional_accounting | high_school_geography | international_law | moral_scenarios | computer_security | high_school_microeconomics | professional_law | medical_genetics | professional_psychology | +|:------------------------:|-------------:|------------:|------------:|--------------------------:|------------------------:|--------------------:|------------------:|--------------------:|-----------------------------:|-------------------:|-------------------:|--------------------------:| +| llama-7b-turbomind | 33.01 | 39.22 | 45.73 | 26.24 | 33.33 | 51.24 | 24.25 | 45.00 | 31.09 | 30.05 | 37.00 | 35.13 | +| llama-13b-turbomind | 66.02 | 51.63 | 71.79 | 34.75 | 55.05 | 64.46 | 30.06 | 63.00 | 47.48 | 37.22 | 53.00 | 48.53 | +| llama-30b-turbomind | 76.70 | 62.42 | 84.19 | 44.68 | 71.72 | 75.21 | 40.56 | 66.00 | 57.98 | 46.48 | 66.00 | 63.73 | +| llama-65b-turbomind | 82.52 | 68.95 | 87.18 | 48.94 | 79.29 | 81.82 | 47.82 | 79.00 | 68.49 | 50.07 | 68.00 | 66.67 | +| llama-2-7b-turbomind | 53.40 | 48.69 | 68.38 | 36.52 | 49.49 | 65.29 | 24.02 | 60.00 | 44.12 | 36.31 | 55.00 | 43.79 | +| llama-2-13b-turbomind | 72.82 | 61.76 | 79.49 | 39.72 | 69.19 | 74.38 | 43.80 | 70.00 | 58.40 | 42.50 | 54.00 | 54.90 | +| llama-2-70b-turbomind | 83.50 | 77.12 | 91.03 | 56.03 | 86.87 | 87.60 | 44.69 | 77.00 | 77.31 | 52.93 | 74.00 | 75.65 | +| llama-3-8b-turbomind | 87.38 | 75.82 | 89.74 | 48.94 | 80.81 | 84.30 | 40.89 | 81.00 | 73.95 | 46.22 | 77.00 | 71.90 | +| llama-3-70b-turbomind | 91.26 | 87.25 | 94.87 | 64.18 | 93.94 | 89.26 | 62.91 | 83.00 | 87.82 | 61.80 | 90.00 | 85.78 | +| internlm2-1.8b-turbomind | 60.19 | 58.17 | 63.25 | 31.21 | 56.57 | 56.20 | 24.47 | 52.00 | 50.42 | 36.11 | 53.00 | 41.83 | +| internlm2-7b-turbomind | 79.61 | 75.49 | 87.61 | 48.23 | 82.83 | 77.69 | 49.39 | 74.00 | 72.27 | 47.65 | 73.00 | 65.03 | +| internlm2-20b-turbomind | 79.61 | 75.49 | 91.88 | 50.00 | 87.88 | 85.95 | 35.08 | 81.00 | 70.59 | 49.48 | 78.00 | 70.10 | +| qwen-1.8b-turbomind | 66.02 | 60.46 | 73.50 | 38.30 | 56.57 | 66.94 | 23.91 | 56.00 | 42.02 | 33.96 | 51.00 | 39.54 | +| qwen-7b-turbomind | 78.64 | 67.32 | 83.33 | 41.49 | 76.77 | 76.03 | 29.72 | 73.00 | 58.40 | 41.72 | 69.00 | 59.64 | +| qwen-14b-turbomind | 78.64 | 73.86 | 88.89 | 48.58 | 83.84 | 84.30 | 45.47 | 77.00 | 73.95 | 50.85 | 74.00 | 69.61 | +| qwen-72b-turbomind | 90.29 | 84.97 | 94.87 | 65.96 | 92.93 | 88.43 | 65.70 | 79.00 | 84.87 | 61.21 | 86.00 | 82.19 | +| qwen1.5-0.5b-hf | 52.43 | 46.41 | 60.68 | 31.21 | 46.46 | 56.20 | 25.70 | 46.00 | 37.39 | 32.79 | 46.00 | 37.75 | +| qwen1.5-1.8b-hf | 66.02 | 58.50 | 75.64 | 33.69 | 56.06 | 72.73 | 24.69 | 57.00 | 39.50 | 36.11 | 53.00 | 42.81 | +| qwen1.5-4b-hf | 74.76 | 62.75 | 84.19 | 46.81 | 76.77 | 71.07 | 25.03 | 67.00 | 55.04 | 41.33 | 64.00 | 56.05 | +| qwen1.5-7b-hf | 78.64 | 70.92 | 86.32 | 44.68 | 81.82 | 77.69 | 32.74 | 76.00 | 64.29 | 45.37 | 68.00 | 61.27 | +| qwen1.5-14b-hf | 80.58 | 75.49 | 85.90 | 51.06 | 86.36 | 80.99 | 45.03 | 80.00 | 76.47 | 48.57 | 78.00 | 69.61 | +| qwen1.5-32b-hf | 86.41 | 81.37 | 95.30 | 56.38 | 91.41 | 88.43 | 44.02 | 76.00 | 82.77 | 57.89 | 83.00 | 75.33 | +| qwen1.5-72b-hf | 87.38 | 85.29 | 94.87 | 64.89 | 92.42 | 90.08 | 62.12 | 83.00 | 84.03 | 60.76 | 86.00 | 81.05 | +| qwen1.5-moe-a2-7b-hf | 78.64 | 70.92 | 86.32 | 46.81 | 81.82 | 77.69 | 25.59 | 71.00 | 65.97 | 45.37 | 65.00 | 61.44 | +| mistral-7b-v0.1-hf | 82.52 | 75.49 | 87.61 | 48.94 | 76.77 | 77.69 | 32.51 | 77.00 | 66.39 | 44.98 | 74.00 | 67.97 | +| mistral-7b-v0.2-hf | 81.55 | 74.18 | 88.46 | 51.06 | 76.77 | 80.99 | 38.77 | 75.00 | 64.71 | 45.37 | 72.00 | 66.34 | +| mixtral-8x7b-v0.1-hf | 87.38 | 81.70 | 91.88 | 51.77 | 85.86 | 85.95 | 40.11 | 80.00 | 79.41 | 53.32 | 77.00 | 77.94 | +| mixtral-8x22b-v0.1-hf | 89.32 | 85.95 | 91.88 | 62.06 | 91.41 | 90.08 | 64.58 | 83.00 | 87.82 | 60.82 | 84.00 | 83.17 | +| yi-6b-hf | 80.58 | 71.57 | 91.03 | 48.23 | 83.33 | 76.86 | 41.34 | 75.00 | 74.79 | 49.35 | 80.00 | 65.69 | +| yi-34b-hf | 91.26 | 85.62 | 92.31 | 65.25 | 89.39 | 91.74 | 64.69 | 82.00 | 85.29 | 59.97 | 87.00 | 82.19 | +| deepseek-7b-base-hf | 61.17 | 53.59 | 72.22 | 34.04 | 59.09 | 65.29 | 26.37 | 61.00 | 44.96 | 35.53 | 56.00 | 49.18 | +| deepseek-67b-base-hf | 88.35 | 79.74 | 91.88 | 57.09 | 89.39 | 85.12 | 46.15 | 76.00 | 82.35 | 55.93 | 72.00 | 79.58 | + +| model | jurisprudence | world_religions | philosophy | virology | high_school_chemistry | public_relations | high_school_macroeconomics | human_sexuality | elementary_mathematics | high_school_physics | high_school_computer_science | high_school_european_history | +|:------------------------:|----------------:|------------------:|-------------:|-----------:|------------------------:|-------------------:|-----------------------------:|------------------:|-------------------------:|----------------------:|-------------------------------:|-------------------------------:| +| llama-7b-turbomind | 41.67 | 49.12 | 40.84 | 34.94 | 29.56 | 40.00 | 34.10 | 35.11 | 26.46 | 27.81 | 34.00 | 41.82 | +| llama-13b-turbomind | 51.85 | 67.84 | 55.31 | 43.37 | 28.57 | 60.91 | 46.15 | 57.25 | 26.98 | 29.80 | 49.00 | 61.21 | +| llama-30b-turbomind | 71.30 | 79.53 | 66.24 | 49.40 | 40.39 | 70.00 | 56.67 | 64.89 | 37.30 | 35.10 | 60.00 | 70.91 | +| llama-65b-turbomind | 75.00 | 81.29 | 73.63 | 53.01 | 41.38 | 74.55 | 65.90 | 77.86 | 40.21 | 35.76 | 69.00 | 76.36 | +| llama-2-7b-turbomind | 53.70 | 69.01 | 60.13 | 41.57 | 36.95 | 54.55 | 45.90 | 55.73 | 27.25 | 31.13 | 40.00 | 59.39 | +| llama-2-13b-turbomind | 74.07 | 76.61 | 63.99 | 45.78 | 44.83 | 62.73 | 50.77 | 62.60 | 34.13 | 36.42 | 57.00 | 63.03 | +| llama-2-70b-turbomind | 83.33 | 85.96 | 78.46 | 53.61 | 52.22 | 69.09 | 74.87 | 87.02 | 43.39 | 43.71 | 78.00 | 84.24 | +| llama-3-8b-turbomind | 75.00 | 83.04 | 74.28 | 56.02 | 54.68 | 71.82 | 64.87 | 79.39 | 42.06 | 45.03 | 68.00 | 76.36 | +| llama-3-70b-turbomind | 86.11 | 91.23 | 86.50 | 57.83 | 71.92 | 74.55 | 82.56 | 88.55 | 62.70 | 56.95 | 86.00 | 86.67 | +| internlm2-1.8b-turbomind | 55.56 | 59.65 | 51.13 | 40.96 | 43.35 | 52.73 | 43.33 | 47.33 | 30.42 | 33.11 | 47.00 | 56.36 | +| internlm2-7b-turbomind | 79.63 | 82.46 | 73.63 | 51.20 | 55.17 | 70.00 | 66.92 | 70.99 | 46.03 | 42.38 | 70.00 | 78.79 | +| internlm2-20b-turbomind | 75.93 | 82.46 | 73.95 | 56.02 | 57.64 | 68.18 | 70.51 | 68.70 | 49.21 | 38.41 | 75.00 | 82.42 | +| qwen-1.8b-turbomind | 59.26 | 56.14 | 50.80 | 40.96 | 37.93 | 60.00 | 41.03 | 51.15 | 33.33 | 34.44 | 39.00 | 64.24 | +| qwen-7b-turbomind | 73.15 | 76.61 | 67.20 | 47.59 | 51.23 | 65.45 | 60.00 | 69.47 | 43.12 | 38.41 | 67.00 | 66.67 | +| qwen-14b-turbomind | 76.85 | 84.21 | 72.03 | 53.01 | 65.52 | 66.36 | 66.92 | 78.63 | 51.32 | 41.72 | 72.00 | 82.42 | +| qwen-72b-turbomind | 83.33 | 88.30 | 83.28 | 58.43 | 65.52 | 74.55 | 81.54 | 89.31 | 68.52 | 58.28 | 81.00 | 84.24 | +| qwen1.5-0.5b-hf | 40.74 | 40.94 | 41.48 | 40.96 | 28.57 | 50.91 | 36.92 | 41.98 | 28.84 | 22.52 | 37.00 | 52.73 | +| qwen1.5-1.8b-hf | 55.56 | 57.31 | 49.84 | 40.96 | 36.45 | 56.36 | 43.59 | 56.49 | 35.19 | 27.81 | 45.00 | 61.21 | +| qwen1.5-4b-hf | 70.37 | 70.76 | 61.74 | 44.58 | 45.32 | 65.45 | 54.62 | 64.89 | 47.88 | 32.45 | 62.00 | 70.30 | +| qwen1.5-7b-hf | 75.93 | 77.19 | 66.24 | 50.60 | 53.20 | 62.73 | 60.00 | 71.76 | 50.26 | 38.41 | 71.00 | 74.55 | +| qwen1.5-14b-hf | 74.07 | 83.63 | 70.74 | 46.39 | 58.62 | 64.55 | 73.59 | 76.34 | 59.26 | 49.01 | 75.00 | 83.64 | +| qwen1.5-32b-hf | 83.33 | 85.96 | 82.96 | 56.63 | 61.58 | 63.64 | 77.95 | 83.97 | 69.31 | 50.99 | 85.00 | 86.06 | +| qwen1.5-72b-hf | 84.26 | 88.89 | 82.32 | 57.23 | 66.01 | 72.73 | 82.05 | 87.02 | 69.31 | 56.95 | 84.00 | 84.24 | +| qwen1.5-moe-a2-7b-hf | 70.37 | 80.12 | 66.56 | 51.20 | 47.78 | 64.55 | 62.31 | 70.99 | 46.30 | 45.03 | 59.00 | 69.70 | +| mistral-7b-v0.1-hf | 77.78 | 83.04 | 69.45 | 54.82 | 53.20 | 67.27 | 66.15 | 78.63 | 38.10 | 31.79 | 68.00 | 78.79 | +| mistral-7b-v0.2-hf | 73.15 | 82.46 | 72.99 | 53.01 | 55.67 | 66.36 | 62.31 | 77.10 | 40.48 | 34.44 | 66.00 | 76.36 | +| mixtral-8x7b-v0.1-hf | 82.41 | 88.30 | 78.14 | 51.20 | 62.56 | 70.00 | 70.77 | 80.92 | 48.68 | 48.34 | 71.00 | 80.61 | +| mixtral-8x22b-v0.1-hf | 84.26 | 89.47 | 84.57 | 59.04 | 67.49 | 78.18 | 79.23 | 88.55 | 61.64 | 52.98 | 87.00 | 86.06 | +| yi-6b-hf | 78.70 | 81.87 | 69.77 | 46.39 | 52.71 | 73.64 | 65.13 | 74.81 | 46.30 | 38.41 | 66.00 | 71.52 | +| yi-34b-hf | 89.81 | 86.55 | 83.92 | 57.23 | 64.04 | 73.64 | 79.49 | 85.50 | 66.40 | 52.32 | 81.00 | 86.06 | +| deepseek-7b-base-hf | 55.56 | 73.10 | 56.59 | 46.99 | 34.98 | 62.73 | 48.21 | 58.78 | 28.57 | 29.14 | 50.00 | 61.82 | +| deepseek-67b-base-hf | 84.26 | 85.96 | 81.03 | 56.02 | 57.64 | 72.73 | 73.85 | 82.44 | 51.59 | 45.03 | 74.00 | 81.82 | + +| model | business_ethics | moral_disputes | high_school_statistics | miscellaneous | formal_logic | high_school_government_and_politics | prehistory | security_studies | high_school_biology | logical_fallacies | high_school_world_history | professional_medicine | +|:------------------------:|------------------:|-----------------:|-------------------------:|----------------:|---------------:|--------------------------------------:|-------------:|-------------------:|----------------------:|--------------------:|----------------------------:|------------------------:| +| llama-7b-turbomind | 42.00 | 40.46 | 32.87 | 42.78 | 26.19 | 46.11 | 35.19 | 33.47 | 32.90 | 42.33 | 43.88 | 43.75 | +| llama-13b-turbomind | 46.00 | 50.00 | 30.56 | 64.88 | 31.75 | 66.84 | 51.85 | 52.65 | 51.94 | 52.76 | 67.51 | 51.10 | +| llama-30b-turbomind | 55.00 | 66.76 | 49.07 | 77.91 | 36.51 | 82.90 | 68.21 | 66.12 | 69.35 | 67.48 | 80.59 | 55.88 | +| llama-65b-turbomind | 59.00 | 73.70 | 61.57 | 81.35 | 43.65 | 88.60 | 73.46 | 71.84 | 74.19 | 77.30 | 83.97 | 62.13 | +| llama-2-7b-turbomind | 53.00 | 51.16 | 27.78 | 63.60 | 27.78 | 67.36 | 48.77 | 47.76 | 50.97 | 51.53 | 64.56 | 52.57 | +| llama-2-13b-turbomind | 54.00 | 64.45 | 45.37 | 74.46 | 36.51 | 80.83 | 64.81 | 62.86 | 67.42 | 66.87 | 72.15 | 54.41 | +| llama-2-70b-turbomind | 72.00 | 77.17 | 63.43 | 86.08 | 48.41 | 94.30 | 83.64 | 78.37 | 81.61 | 80.98 | 87.76 | 74.63 | +| llama-3-8b-turbomind | 62.00 | 73.70 | 54.17 | 82.76 | 48.41 | 90.16 | 72.53 | 75.51 | 77.74 | 73.01 | 82.70 | 72.06 | +| llama-3-70b-turbomind | 83.00 | 85.55 | 72.22 | 92.21 | 66.67 | 97.41 | 91.05 | 84.90 | 90.32 | 87.73 | 94.09 | 87.13 | +| internlm2-1.8b-turbomind | 44.00 | 45.95 | 38.89 | 59.39 | 32.54 | 60.62 | 50.31 | 54.29 | 52.58 | 45.40 | 62.87 | 37.87 | +| internlm2-7b-turbomind | 69.00 | 66.76 | 57.87 | 80.72 | 50.00 | 90.16 | 73.15 | 75.10 | 79.68 | 68.71 | 81.01 | 70.22 | +| internlm2-20b-turbomind | 74.00 | 74.57 | 60.19 | 81.48 | 44.44 | 91.71 | 75.31 | 81.63 | 82.58 | 75.46 | 87.76 | 63.60 | +| qwen-1.8b-turbomind | 52.00 | 52.31 | 34.72 | 57.98 | 29.37 | 59.07 | 47.22 | 48.57 | 52.26 | 44.17 | 61.18 | 43.38 | +| qwen-7b-turbomind | 68.00 | 64.74 | 45.37 | 77.39 | 43.65 | 83.94 | 68.21 | 70.20 | 72.26 | 65.64 | 75.95 | 58.46 | +| qwen-14b-turbomind | 75.00 | 74.86 | 57.87 | 84.04 | 51.59 | 91.71 | 70.99 | 77.14 | 83.55 | 73.01 | 83.12 | 67.65 | +| qwen-72b-turbomind | 80.00 | 84.97 | 68.98 | 91.44 | 54.76 | 98.96 | 87.04 | 81.63 | 89.03 | 84.05 | 90.30 | 84.93 | +| qwen1.5-0.5b-hf | 47.00 | 46.82 | 23.15 | 48.02 | 29.37 | 48.70 | 40.12 | 38.37 | 40.65 | 35.58 | 53.16 | 31.62 | +| qwen1.5-1.8b-hf | 54.00 | 54.91 | 28.70 | 61.69 | 23.81 | 58.03 | 48.15 | 51.84 | 55.48 | 45.40 | 59.92 | 39.71 | +| qwen1.5-4b-hf | 65.00 | 66.76 | 44.44 | 73.95 | 35.71 | 78.24 | 60.19 | 65.31 | 66.45 | 65.64 | 71.31 | 50.00 | +| qwen1.5-7b-hf | 68.00 | 70.81 | 48.61 | 76.50 | 38.89 | 84.97 | 69.44 | 68.16 | 74.52 | 68.10 | 77.22 | 56.25 | +| qwen1.5-14b-hf | 77.00 | 73.70 | 62.96 | 83.40 | 53.17 | 90.67 | 71.60 | 80.82 | 84.52 | 76.69 | 83.54 | 71.69 | +| qwen1.5-32b-hf | 77.00 | 78.90 | 68.98 | 88.12 | 54.76 | 94.82 | 81.48 | 80.82 | 88.39 | 82.21 | 86.08 | 80.88 | +| qwen1.5-72b-hf | 80.00 | 84.39 | 68.98 | 91.44 | 55.56 | 98.96 | 86.73 | 81.63 | 88.71 | 85.89 | 89.87 | 82.72 | +| qwen1.5-moe-a2-7b-hf | 74.00 | 65.90 | 56.48 | 82.25 | 34.13 | 84.46 | 70.68 | 74.29 | 73.23 | 68.10 | 76.79 | 66.91 | +| mistral-7b-v0.1-hf | 57.00 | 71.10 | 57.41 | 81.61 | 40.48 | 86.53 | 73.46 | 72.65 | 76.77 | 79.14 | 77.22 | 68.75 | +| mistral-7b-v0.2-hf | 61.00 | 71.39 | 52.78 | 80.08 | 40.48 | 88.08 | 69.44 | 72.24 | 76.13 | 77.91 | 78.06 | 70.59 | +| mixtral-8x7b-v0.1-hf | 77.00 | 80.06 | 63.43 | 87.87 | 54.76 | 93.26 | 83.95 | 80.00 | 84.19 | 79.14 | 88.61 | 81.25 | +| mixtral-8x22b-v0.1-hf | 72.00 | 84.10 | 68.52 | 90.68 | 57.14 | 96.37 | 86.73 | 86.53 | 90.32 | 87.73 | 90.30 | 87.87 | +| yi-6b-hf | 67.00 | 69.36 | 52.78 | 80.46 | 44.44 | 89.64 | 70.99 | 74.69 | 77.10 | 78.53 | 78.90 | 65.81 | +| yi-34b-hf | 79.00 | 83.82 | 66.67 | 90.29 | 57.14 | 97.93 | 87.65 | 84.90 | 88.39 | 87.73 | 92.83 | 81.99 | +| deepseek-7b-base-hf | 49.00 | 52.31 | 41.20 | 66.28 | 30.95 | 63.73 | 55.86 | 51.84 | 52.90 | 58.90 | 62.45 | 45.22 | +| deepseek-67b-base-hf | 81.00 | 77.17 | 63.89 | 90.04 | 53.17 | 97.93 | 85.49 | 73.88 | 82.26 | 84.05 | 91.56 | 78.31 | + +| model | high_school_mathematics | college_medicine | high_school_us_history | sociology | econometrics | high_school_psychology | human_aging | us_foreign_policy | +|:------------------------:|--------------------------:|-------------------:|-------------------------:|------------:|---------------:|-------------------------:|--------------:|--------------------:| +| llama-7b-turbomind | 24.81 | 32.95 | 38.73 | 45.77 | 27.19 | 48.07 | 38.12 | 43.00 | +| llama-13b-turbomind | 26.30 | 42.20 | 59.80 | 61.19 | 28.95 | 61.28 | 53.36 | 78.00 | +| llama-30b-turbomind | 27.41 | 54.91 | 76.96 | 79.10 | 35.96 | 76.15 | 67.71 | 83.00 | +| llama-65b-turbomind | 34.44 | 54.34 | 82.84 | 81.09 | 39.47 | 82.39 | 66.37 | 88.00 | +| llama-2-7b-turbomind | 29.63 | 43.35 | 60.29 | 62.69 | 27.19 | 62.75 | 56.05 | 64.00 | +| llama-2-13b-turbomind | 27.04 | 52.60 | 75.49 | 73.13 | 32.46 | 76.51 | 64.57 | 82.00 | +| llama-2-70b-turbomind | 34.07 | 64.16 | 90.69 | 90.55 | 44.74 | 87.52 | 80.27 | 92.00 | +| llama-3-8b-turbomind | 38.15 | 64.16 | 83.33 | 86.57 | 47.37 | 84.04 | 70.85 | 87.00 | +| llama-3-70b-turbomind | 48.89 | 79.77 | 95.10 | 94.03 | 72.81 | 94.13 | 82.51 | 94.00 | +| internlm2-1.8b-turbomind | 30.37 | 41.04 | 55.88 | 51.74 | 28.95 | 61.47 | 51.12 | 63.00 | +| internlm2-7b-turbomind | 39.63 | 68.21 | 76.96 | 84.58 | 44.74 | 84.59 | 72.65 | 86.00 | +| internlm2-20b-turbomind | 39.63 | 66.47 | 82.84 | 85.07 | 47.37 | 86.79 | 70.85 | 84.00 | +| qwen-1.8b-turbomind | 28.52 | 43.35 | 54.90 | 60.70 | 36.84 | 60.73 | 48.43 | 60.00 | +| qwen-7b-turbomind | 30.00 | 57.23 | 75.98 | 79.10 | 32.46 | 79.27 | 63.23 | 81.00 | +| qwen-14b-turbomind | 37.41 | 70.52 | 81.37 | 85.07 | 50.00 | 84.95 | 73.09 | 86.00 | +| qwen-72b-turbomind | 50.00 | 75.72 | 92.16 | 90.05 | 59.65 | 92.66 | 82.51 | 95.00 | +| qwen1.5-0.5b-hf | 29.63 | 33.53 | 45.10 | 59.70 | 28.95 | 44.77 | 37.22 | 69.00 | +| qwen1.5-1.8b-hf | 34.07 | 39.31 | 47.55 | 63.18 | 32.46 | 59.08 | 53.81 | 73.00 | +| qwen1.5-4b-hf | 35.93 | 55.49 | 71.08 | 73.13 | 37.72 | 72.11 | 63.68 | 79.00 | +| qwen1.5-7b-hf | 34.81 | 61.85 | 78.92 | 82.09 | 41.23 | 80.73 | 61.88 | 84.00 | +| qwen1.5-14b-hf | 45.93 | 68.21 | 80.88 | 83.08 | 55.26 | 86.06 | 73.09 | 88.00 | +| qwen1.5-32b-hf | 47.04 | 76.30 | 90.20 | 86.07 | 57.89 | 90.28 | 75.78 | 92.00 | +| qwen1.5-72b-hf | 47.78 | 75.14 | 92.65 | 88.56 | 59.65 | 92.48 | 79.82 | 94.00 | +| qwen1.5-moe-a2-7b-hf | 46.30 | 54.91 | 78.43 | 79.10 | 38.60 | 82.39 | 66.82 | 83.00 | +| mistral-7b-v0.1-hf | 33.70 | 65.32 | 78.92 | 83.08 | 50.00 | 82.39 | 69.51 | 86.00 | +| mistral-7b-v0.2-hf | 38.15 | 64.16 | 81.86 | 82.09 | 43.86 | 80.18 | 69.96 | 86.00 | +| mixtral-8x7b-v0.1-hf | 40.37 | 69.94 | 86.27 | 88.56 | 65.79 | 88.81 | 79.37 | 91.00 | +| mixtral-8x22b-v0.1-hf | 45.93 | 79.19 | 90.20 | 93.03 | 70.18 | 92.29 | 79.37 | 95.00 | +| yi-6b-hf | 32.59 | 61.27 | 79.90 | 82.59 | 35.96 | 82.94 | 67.26 | 86.00 | +| yi-34b-hf | 45.19 | 71.68 | 91.18 | 88.56 | 55.26 | 91.74 | 78.48 | 91.00 | +| deepseek-7b-base-hf | 28.89 | 41.62 | 60.29 | 70.15 | 26.32 | 69.72 | 55.61 | 76.00 | +| deepseek-67b-base-hf | 38.89 | 72.25 | 90.69 | 90.05 | 52.63 | 90.46 | 80.72 | 95.00 | + +## Chat Models + +| model | mmlu | mmlu-stem | mmlu-social-science | mmlu-humanities | mmlu-other | +|:-----------------------------:|-------:|------------:|----------------------:|------------------:|-------------:| +| qwen1.5-0.5b-chat-hf | 35.32 | 30.90 | 37.59 | 37.29 | 37.73 | +| qwen1.5-1.8b-chat-hf | 45.62 | 39.20 | 49.21 | 47.67 | 49.63 | +| qwen1.5-4b-chat-hf | 55.90 | 48.07 | 62.67 | 59.70 | 57.31 | +| qwen1.5-7b-chat-hf | 61.79 | 52.68 | 69.41 | 66.41 | 63.45 | +| qwen1.5-14b-chat-hf | 67.96 | 59.79 | 75.46 | 71.23 | 69.72 | +| qwen1.5-32b-chat-hf | 75.36 | 67.04 | 82.11 | 80.44 | 76.23 | +| qwen1.5-72b-chat-hf | 77.24 | 69.59 | 83.95 | 81.58 | 77.87 | +| qwen1.5-110b-chat-hf | 77.95 | 71.56 | 83.77 | 81.44 | 78.41 | +| internlm2-chat-1.8b-hf | 47.58 | 40.88 | 53.33 | 49.92 | 49.74 | +| internlm2-chat-1.8b-sft-hf | 47.44 | 40.55 | 53.31 | 49.67 | 49.89 | +| internlm2-chat-7b-hf | 63.05 | 53.42 | 71.47 | 67.27 | 65.13 | +| internlm2-chat-7b-sft-hf | 63.33 | 53.95 | 71.74 | 67.62 | 65.00 | +| internlm2-chat-20b-hf | 67.37 | 57.39 | 75.75 | 71.63 | 69.95 | +| internlm2-chat-20b-sft-hf | 67.34 | 57.49 | 75.67 | 70.99 | 70.40 | +| llama-3-8b-instruct-hf | 68.37 | 58.01 | 77.82 | 71.22 | 71.94 | +| llama-3-70b-instruct-hf | 80.93 | 73.86 | 87.71 | 83.90 | 82.01 | +| llama-3-8b-instruct-lmdeploy | 67.35 | 56.66 | 75.96 | 70.90 | 71.49 | +| llama-3-70b-instruct-lmdeploy | 80.85 | 74.07 | 87.26 | 83.73 | 81.96 | +| mistral-7b-instruct-v0.1-hf | 54.36 | 43.74 | 62.96 | 58.87 | 57.46 | +| mistral-7b-instruct-v0.2-hf | 59.98 | 49.56 | 69.22 | 64.41 | 62.24 | +| mixtral-8x7b-instruct-v0.1-hf | 70.11 | 60.29 | 79.01 | 74.08 | 72.28 | + +### Details + +| model | college_biology | college_chemistry | college_computer_science | college_mathematics | college_physics | electrical_engineering | astronomy | anatomy | abstract_algebra | machine_learning | clinical_knowledge | global_facts | +|:-----------------------------:|------------------:|--------------------:|---------------------------:|----------------------:|------------------:|-------------------------:|------------:|----------:|-------------------:|-------------------:|---------------------:|---------------:| +| qwen1.5-0.5b-chat-hf | 31.25 | 32.00 | 33.00 | 29.00 | 33.33 | 38.62 | 33.55 | 28.89 | 20.00 | 27.68 | 40.38 | 33.00 | +| qwen1.5-1.8b-chat-hf | 42.36 | 28.00 | 45.00 | 33.00 | 27.45 | 44.83 | 51.97 | 42.22 | 32.00 | 38.39 | 48.30 | 30.00 | +| qwen1.5-4b-chat-hf | 56.25 | 47.00 | 49.00 | 39.00 | 36.27 | 54.48 | 57.89 | 49.63 | 38.00 | 33.04 | 59.62 | 23.00 | +| qwen1.5-7b-chat-hf | 64.58 | 51.00 | 59.00 | 37.00 | 41.18 | 53.79 | 66.45 | 53.33 | 43.00 | 41.07 | 67.92 | 36.00 | +| qwen1.5-14b-chat-hf | 77.08 | 51.00 | 64.00 | 42.00 | 45.10 | 64.83 | 77.63 | 65.93 | 39.00 | 46.43 | 73.21 | 45.00 | +| qwen1.5-32b-chat-hf | 84.72 | 53.00 | 57.00 | 48.00 | 52.94 | 74.48 | 82.24 | 67.41 | 52.00 | 61.61 | 78.11 | 48.00 | +| qwen1.5-72b-chat-hf | 90.97 | 57.00 | 66.00 | 55.00 | 55.88 | 80.00 | 88.16 | 72.59 | 56.00 | 59.82 | 80.00 | 51.00 | +| qwen1.5-110b-chat-hf | 88.89 | 62.00 | 66.00 | 64.00 | 58.82 | 75.86 | 89.47 | 68.15 | 59.00 | 63.39 | 79.62 | 59.00 | +| internlm2-chat-1.8b-hf | 49.31 | 36.00 | 47.00 | 33.00 | 36.27 | 42.76 | 48.03 | 49.63 | 30.00 | 33.93 | 53.58 | 28.00 | +| internlm2-chat-1.8b-sft-hf | 51.39 | 37.00 | 50.00 | 33.00 | 33.33 | 42.76 | 46.05 | 49.63 | 31.00 | 32.14 | 53.21 | 29.00 | +| internlm2-chat-7b-hf | 68.75 | 47.00 | 62.00 | 32.00 | 38.24 | 57.24 | 69.74 | 58.52 | 29.00 | 53.57 | 70.19 | 41.00 | +| internlm2-chat-7b-sft-hf | 71.53 | 47.00 | 63.00 | 34.00 | 37.25 | 57.24 | 69.74 | 57.78 | 29.00 | 52.68 | 69.43 | 34.00 | +| internlm2-chat-20b-hf | 76.39 | 51.00 | 61.00 | 37.00 | 40.20 | 62.76 | 78.95 | 67.41 | 33.00 | 46.43 | 75.09 | 42.00 | +| internlm2-chat-20b-sft-hf | 77.08 | 49.00 | 60.00 | 39.00 | 39.22 | 64.14 | 79.61 | 68.15 | 35.00 | 46.43 | 75.09 | 42.00 | +| llama-3-8b-instruct-hf | 81.94 | 48.00 | 58.00 | 43.00 | 48.04 | 60.69 | 76.32 | 71.11 | 33.00 | 54.46 | 73.58 | 46.00 | +| llama-3-70b-instruct-hf | 93.06 | 56.00 | 70.00 | 60.00 | 60.78 | 77.24 | 93.42 | 79.26 | 53.00 | 71.43 | 86.42 | 66.00 | +| llama-3-8b-instruct-lmdeploy | 79.17 | 47.00 | 53.00 | 36.00 | 49.02 | 60.00 | 73.68 | 68.89 | 36.00 | 55.36 | 73.96 | 42.00 | +| llama-3-70b-instruct-lmdeploy | 93.75 | 57.00 | 66.00 | 61.00 | 65.69 | 77.93 | 92.11 | 78.52 | 55.00 | 70.54 | 86.42 | 64.00 | +| mistral-7b-instruct-v0.1-hf | 57.64 | 35.00 | 50.00 | 31.00 | 24.51 | 51.72 | 58.55 | 45.93 | 35.00 | 41.07 | 56.98 | 32.00 | +| mistral-7b-instruct-v0.2-hf | 70.14 | 42.00 | 49.00 | 35.00 | 43.14 | 54.48 | 65.79 | 56.30 | 29.00 | 42.86 | 65.28 | 37.00 | +| mixtral-8x7b-instruct-v0.1-hf | 81.25 | 57.00 | 57.00 | 40.00 | 50.00 | 60.69 | 80.92 | 65.93 | 45.00 | 50.89 | 76.60 | 41.00 | + +| model | management | nutrition | marketing | professional_accounting | high_school_geography | international_law | moral_scenarios | computer_security | high_school_microeconomics | professional_law | medical_genetics | professional_psychology | +|:-----------------------------:|-------------:|------------:|------------:|--------------------------:|------------------------:|--------------------:|------------------:|--------------------:|-----------------------------:|-------------------:|-------------------:|--------------------------:| +| qwen1.5-0.5b-chat-hf | 41.75 | 38.89 | 49.15 | 26.60 | 48.48 | 50.41 | 24.69 | 42.00 | 32.35 | 31.75 | 31.00 | 32.35 | +| qwen1.5-1.8b-chat-hf | 62.14 | 55.56 | 76.92 | 34.40 | 58.08 | 61.16 | 21.90 | 56.00 | 42.44 | 35.14 | 50.00 | 44.93 | +| qwen1.5-4b-chat-hf | 73.79 | 58.50 | 82.05 | 47.16 | 74.24 | 71.90 | 32.29 | 69.00 | 58.40 | 40.74 | 58.00 | 53.76 | +| qwen1.5-7b-chat-hf | 79.61 | 69.28 | 85.47 | 41.49 | 78.79 | 76.86 | 35.75 | 74.00 | 65.13 | 44.78 | 68.00 | 57.68 | +| qwen1.5-14b-chat-hf | 82.52 | 70.26 | 87.18 | 51.77 | 85.86 | 82.64 | 53.74 | 81.00 | 76.05 | 47.98 | 76.00 | 67.48 | +| qwen1.5-32b-chat-hf | 84.47 | 77.78 | 94.44 | 60.99 | 90.91 | 87.60 | 72.96 | 79.00 | 83.61 | 58.28 | 83.00 | 77.94 | +| qwen1.5-72b-chat-hf | 89.32 | 85.95 | 93.59 | 61.35 | 90.91 | 86.78 | 75.98 | 83.00 | 84.87 | 60.30 | 83.00 | 81.05 | +| qwen1.5-110b-chat-hf | 86.41 | 80.72 | 92.74 | 69.15 | 93.94 | 84.30 | 77.88 | 83.00 | 88.66 | 61.73 | 84.00 | 82.19 | +| internlm2-chat-1.8b-hf | 72.82 | 50.65 | 69.23 | 35.46 | 56.06 | 56.20 | 27.82 | 60.00 | 49.16 | 33.83 | 54.00 | 43.79 | +| internlm2-chat-1.8b-sft-hf | 71.84 | 52.61 | 68.80 | 34.75 | 55.56 | 53.72 | 27.04 | 58.00 | 48.74 | 34.09 | 54.00 | 44.61 | +| internlm2-chat-7b-hf | 78.64 | 66.67 | 85.90 | 46.81 | 79.29 | 70.25 | 35.31 | 79.00 | 68.07 | 46.41 | 68.00 | 64.87 | +| internlm2-chat-7b-sft-hf | 79.61 | 67.97 | 86.75 | 47.52 | 80.30 | 70.25 | 35.98 | 80.00 | 69.33 | 45.83 | 70.00 | 65.36 | +| internlm2-chat-20b-hf | 80.58 | 75.16 | 90.17 | 52.13 | 83.84 | 80.99 | 39.33 | 80.00 | 70.59 | 49.67 | 75.00 | 70.26 | +| internlm2-chat-20b-sft-hf | 80.58 | 76.14 | 91.03 | 53.19 | 84.34 | 80.99 | 36.31 | 77.00 | 71.85 | 49.61 | 77.00 | 70.59 | +| llama-3-8b-instruct-hf | 82.52 | 79.41 | 91.45 | 52.48 | 80.30 | 79.34 | 46.26 | 75.00 | 76.89 | 49.61 | 85.00 | 72.22 | +| llama-3-70b-instruct-hf | 89.32 | 87.58 | 93.16 | 66.67 | 92.42 | 90.08 | 76.20 | 83.00 | 89.50 | 64.67 | 92.00 | 87.09 | +| llama-3-8b-instruct-lmdeploy | 87.38 | 79.41 | 90.17 | 52.48 | 79.80 | 78.51 | 44.25 | 75.00 | 74.37 | 48.76 | 84.00 | 69.61 | +| llama-3-70b-instruct-lmdeploy | 90.29 | 88.56 | 93.59 | 65.96 | 92.93 | 89.26 | 75.75 | 83.00 | 89.92 | 63.95 | 92.00 | 86.60 | +| mistral-7b-instruct-v0.1-hf | 69.90 | 59.80 | 85.47 | 38.65 | 69.70 | 65.29 | 37.54 | 69.00 | 51.26 | 37.81 | 65.00 | 52.45 | +| mistral-7b-instruct-v0.2-hf | 74.76 | 66.99 | 88.89 | 43.97 | 75.25 | 76.86 | 42.01 | 73.00 | 62.61 | 42.24 | 67.00 | 62.25 | +| mixtral-8x7b-instruct-v0.1-hf | 85.44 | 80.39 | 92.74 | 55.32 | 85.35 | 82.64 | 48.38 | 78.00 | 75.21 | 53.52 | 75.00 | 74.02 | + +| model | jurisprudence | world_religions | philosophy | virology | high_school_chemistry | public_relations | high_school_macroeconomics | human_sexuality | elementary_mathematics | high_school_physics | high_school_computer_science | high_school_european_history | +|:-----------------------------:|----------------:|------------------:|-------------:|-----------:|------------------------:|-------------------:|-----------------------------:|------------------:|-------------------------:|----------------------:|-------------------------------:|-------------------------------:| +| qwen1.5-0.5b-chat-hf | 42.59 | 24.56 | 39.87 | 39.76 | 29.06 | 38.18 | 35.64 | 38.93 | 27.78 | 29.80 | 34.00 | 48.48 | +| qwen1.5-1.8b-chat-hf | 50.93 | 56.73 | 44.37 | 42.77 | 35.96 | 51.82 | 38.46 | 49.62 | 35.45 | 27.15 | 47.00 | 63.03 | +| qwen1.5-4b-chat-hf | 71.30 | 65.50 | 58.20 | 50.00 | 44.33 | 57.27 | 54.10 | 61.83 | 43.65 | 41.06 | 60.00 | 72.12 | +| qwen1.5-7b-chat-hf | 76.85 | 76.61 | 68.49 | 48.80 | 51.72 | 64.55 | 59.23 | 68.70 | 48.94 | 37.09 | 69.00 | 79.39 | +| qwen1.5-14b-chat-hf | 75.93 | 80.70 | 69.13 | 51.20 | 55.67 | 64.55 | 67.69 | 74.05 | 57.14 | 47.02 | 74.00 | 82.42 | +| qwen1.5-32b-chat-hf | 83.33 | 89.47 | 82.64 | 60.84 | 62.56 | 70.00 | 76.67 | 83.21 | 67.46 | 59.60 | 85.00 | 84.85 | +| qwen1.5-72b-chat-hf | 86.11 | 89.47 | 80.71 | 59.04 | 68.47 | 72.73 | 80.00 | 87.79 | 67.72 | 52.32 | 79.00 | 85.45 | +| qwen1.5-110b-chat-hf | 83.33 | 87.13 | 81.03 | 54.22 | 69.95 | 73.64 | 78.21 | 87.02 | 75.93 | 57.62 | 84.00 | 88.48 | +| internlm2-chat-1.8b-hf | 52.78 | 60.82 | 49.20 | 42.77 | 42.36 | 50.00 | 47.18 | 53.44 | 32.54 | 31.79 | 39.00 | 60.00 | +| internlm2-chat-1.8b-sft-hf | 53.70 | 61.40 | 50.16 | 42.17 | 40.89 | 50.00 | 47.69 | 51.15 | 32.54 | 29.14 | 40.00 | 59.39 | +| internlm2-chat-7b-hf | 73.15 | 81.87 | 67.85 | 47.59 | 49.75 | 62.73 | 61.79 | 66.41 | 44.97 | 33.77 | 71.00 | 81.82 | +| internlm2-chat-7b-sft-hf | 73.15 | 81.87 | 66.88 | 48.19 | 48.77 | 63.64 | 62.31 | 65.65 | 45.77 | 33.77 | 72.00 | 81.82 | +| internlm2-chat-20b-hf | 80.56 | 81.87 | 72.99 | 55.42 | 54.19 | 70.00 | 67.95 | 71.76 | 48.15 | 39.74 | 75.00 | 80.00 | +| internlm2-chat-20b-sft-hf | 81.48 | 79.53 | 72.99 | 54.82 | 54.19 | 69.09 | 67.95 | 71.76 | 48.94 | 41.06 | 75.00 | 80.00 | +| llama-3-8b-instruct-hf | 76.85 | 79.53 | 72.35 | 53.61 | 54.19 | 70.91 | 66.41 | 80.92 | 49.47 | 46.36 | 71.00 | 75.15 | +| llama-3-70b-instruct-hf | 87.04 | 88.30 | 82.64 | 56.02 | 67.49 | 74.55 | 86.41 | 88.55 | 74.34 | 65.56 | 91.00 | 86.06 | +| llama-3-8b-instruct-lmdeploy | 77.78 | 79.53 | 70.74 | 52.41 | 53.20 | 68.18 | 65.38 | 79.39 | 50.79 | 37.75 | 72.00 | 76.97 | +| llama-3-70b-instruct-lmdeploy | 87.96 | 90.64 | 83.28 | 54.82 | 69.46 | 73.64 | 86.92 | 87.02 | 74.87 | 66.23 | 92.00 | 85.45 | +| mistral-7b-instruct-v0.1-hf | 64.81 | 70.18 | 63.67 | 41.57 | 38.92 | 68.18 | 49.49 | 61.83 | 33.33 | 32.45 | 55.00 | 66.67 | +| mistral-7b-instruct-v0.2-hf | 70.37 | 80.12 | 64.95 | 50.60 | 50.74 | 68.18 | 54.36 | 71.76 | 40.74 | 35.10 | 60.00 | 73.33 | +| mixtral-8x7b-instruct-v0.1-hf | 79.63 | 87.72 | 73.63 | 54.82 | 61.58 | 67.27 | 69.49 | 83.21 | 52.91 | 47.02 | 74.00 | 80.61 | + +| model | business_ethics | moral_disputes | high_school_statistics | miscellaneous | formal_logic | high_school_government_and_politics | prehistory | security_studies | high_school_biology | logical_fallacies | high_school_world_history | professional_medicine | +|:-----------------------------:|------------------:|-----------------:|-------------------------:|----------------:|---------------:|--------------------------------------:|-------------:|-------------------:|----------------------:|--------------------:|----------------------------:|------------------------:| +| qwen1.5-0.5b-chat-hf | 45.00 | 41.04 | 30.09 | 39.21 | 24.60 | 35.23 | 33.95 | 25.31 | 36.13 | 31.29 | 49.37 | 38.24 | +| qwen1.5-1.8b-chat-hf | 54.00 | 50.29 | 34.26 | 58.49 | 24.60 | 55.96 | 47.53 | 39.18 | 47.74 | 44.17 | 64.98 | 40.81 | +| qwen1.5-4b-chat-hf | 61.00 | 64.16 | 46.30 | 71.01 | 39.68 | 72.02 | 54.01 | 65.31 | 63.55 | 63.80 | 71.31 | 51.10 | +| qwen1.5-7b-chat-hf | 69.00 | 67.05 | 50.93 | 76.25 | 53.17 | 82.38 | 62.96 | 71.02 | 73.23 | 68.10 | 76.79 | 60.29 | +| qwen1.5-14b-chat-hf | 74.00 | 75.14 | 58.33 | 82.89 | 51.59 | 88.60 | 69.44 | 77.96 | 84.19 | 73.62 | 82.70 | 71.32 | +| qwen1.5-32b-chat-hf | 80.00 | 80.64 | 70.83 | 89.40 | 60.32 | 94.82 | 81.79 | 79.59 | 90.00 | 86.50 | 88.61 | 80.15 | +| qwen1.5-72b-chat-hf | 80.00 | 82.95 | 68.98 | 91.83 | 57.14 | 98.45 | 86.73 | 78.78 | 89.03 | 87.12 | 91.14 | 83.82 | +| qwen1.5-110b-chat-hf | 79.00 | 78.03 | 67.13 | 92.98 | 62.70 | 97.93 | 87.04 | 74.29 | 88.71 | 82.82 | 91.14 | 84.93 | +| internlm2-chat-1.8b-hf | 48.00 | 49.13 | 44.91 | 57.60 | 26.98 | 61.14 | 50.62 | 51.02 | 52.58 | 57.67 | 67.51 | 37.50 | +| internlm2-chat-1.8b-sft-hf | 50.00 | 49.13 | 44.91 | 57.73 | 28.57 | 61.66 | 49.69 | 51.02 | 49.68 | 57.67 | 66.67 | 38.60 | +| internlm2-chat-7b-hf | 65.00 | 65.61 | 49.54 | 80.84 | 43.65 | 88.08 | 70.99 | 68.98 | 78.39 | 75.46 | 82.28 | 61.76 | +| internlm2-chat-7b-sft-hf | 64.00 | 66.18 | 52.31 | 81.35 | 46.03 | 88.08 | 71.60 | 67.76 | 78.39 | 77.30 | 82.28 | 63.60 | +| internlm2-chat-20b-hf | 74.00 | 73.70 | 59.72 | 81.86 | 46.83 | 89.12 | 74.69 | 75.92 | 80.65 | 79.14 | 82.70 | 70.59 | +| internlm2-chat-20b-sft-hf | 76.00 | 73.12 | 60.19 | 81.99 | 43.65 | 88.60 | 74.38 | 73.88 | 80.32 | 80.37 | 82.70 | 70.59 | +| llama-3-8b-instruct-hf | 72.00 | 73.12 | 55.09 | 84.55 | 50.00 | 90.67 | 77.16 | 77.55 | 81.61 | 77.91 | 84.81 | 75.00 | +| llama-3-70b-instruct-hf | 85.00 | 85.26 | 75.00 | 92.72 | 69.05 | 97.41 | 90.43 | 82.04 | 91.61 | 87.12 | 94.09 | 89.71 | +| llama-3-8b-instruct-lmdeploy | 72.00 | 72.83 | 52.78 | 82.12 | 51.59 | 89.64 | 76.85 | 76.73 | 80.97 | 76.69 | 84.39 | 74.63 | +| llama-3-70b-instruct-lmdeploy | 85.00 | 84.39 | 73.61 | 92.72 | 67.46 | 97.93 | 89.81 | 81.63 | 90.65 | 87.12 | 93.25 | 89.34 | +| mistral-7b-instruct-v0.1-hf | 55.00 | 57.51 | 39.81 | 74.07 | 39.68 | 75.65 | 57.72 | 62.04 | 59.35 | 69.33 | 67.93 | 55.88 | +| mistral-7b-instruct-v0.2-hf | 61.00 | 66.76 | 46.76 | 78.67 | 36.51 | 84.97 | 68.83 | 70.20 | 68.39 | 69.33 | 73.00 | 58.09 | +| mixtral-8x7b-instruct-v0.1-hf | 66.00 | 76.59 | 57.87 | 86.59 | 50.00 | 93.78 | 83.02 | 79.18 | 82.58 | 75.46 | 86.50 | 77.94 | + +| model | high_school_mathematics | college_medicine | high_school_us_history | sociology | econometrics | high_school_psychology | human_aging | us_foreign_policy | +|:-----------------------------:|--------------------------:|-------------------:|-------------------------:|------------:|---------------:|-------------------------:|--------------:|--------------------:| +| qwen1.5-0.5b-chat-hf | 24.44 | 35.26 | 42.16 | 47.26 | 29.82 | 40.55 | 32.29 | 47.00 | +| qwen1.5-1.8b-chat-hf | 32.22 | 43.35 | 54.90 | 48.26 | 28.95 | 61.83 | 48.43 | 71.00 | +| qwen1.5-4b-chat-hf | 36.30 | 51.45 | 71.08 | 76.62 | 34.21 | 72.29 | 58.30 | 72.00 | +| qwen1.5-7b-chat-hf | 31.11 | 61.27 | 76.47 | 79.10 | 42.11 | 81.28 | 61.43 | 83.00 | +| qwen1.5-14b-chat-hf | 41.48 | 68.79 | 80.88 | 82.59 | 48.25 | 84.40 | 72.20 | 88.00 | +| qwen1.5-32b-chat-hf | 48.52 | 75.72 | 88.73 | 86.07 | 57.02 | 90.46 | 78.03 | 95.00 | +| qwen1.5-72b-chat-hf | 51.48 | 73.99 | 90.69 | 87.06 | 59.65 | 92.11 | 79.37 | 94.00 | +| qwen1.5-110b-chat-hf | 52.22 | 76.30 | 93.14 | 87.56 | 62.28 | 91.56 | 80.27 | 88.00 | +| internlm2-chat-1.8b-hf | 31.48 | 46.82 | 56.37 | 65.17 | 28.07 | 65.87 | 50.22 | 69.00 | +| internlm2-chat-1.8b-sft-hf | 30.74 | 47.40 | 54.41 | 64.18 | 29.82 | 66.24 | 48.43 | 69.00 | +| internlm2-chat-7b-hf | 33.70 | 67.05 | 79.90 | 81.09 | 48.25 | 84.04 | 67.26 | 84.00 | +| internlm2-chat-7b-sft-hf | 35.19 | 67.05 | 79.90 | 80.60 | 48.25 | 84.59 | 65.47 | 85.00 | +| internlm2-chat-20b-hf | 36.30 | 66.47 | 88.73 | 85.07 | 51.75 | 85.69 | 70.85 | 87.00 | +| internlm2-chat-20b-sft-hf | 35.93 | 65.90 | 87.75 | 85.57 | 52.63 | 84.77 | 70.85 | 87.00 | +| llama-3-8b-instruct-hf | 36.67 | 68.79 | 83.82 | 86.57 | 61.40 | 84.95 | 70.85 | 85.00 | +| llama-3-70b-instruct-hf | 57.41 | 78.61 | 89.71 | 91.54 | 74.56 | 94.50 | 82.96 | 94.00 | +| llama-3-8b-instruct-lmdeploy | 38.52 | 68.79 | 82.84 | 85.57 | 54.39 | 85.50 | 69.96 | 83.00 | +| llama-3-70b-instruct-lmdeploy | 54.81 | 79.77 | 90.20 | 92.04 | 71.05 | 94.50 | 82.96 | 93.00 | +| mistral-7b-instruct-v0.1-hf | 28.89 | 50.29 | 67.16 | 76.12 | 39.47 | 72.29 | 62.33 | 77.00 | +| mistral-7b-instruct-v0.2-hf | 30.74 | 53.18 | 73.04 | 77.11 | 42.11 | 79.82 | 63.68 | 82.00 | +| mixtral-8x7b-instruct-v0.1-hf | 35.56 | 73.41 | 85.29 | 87.06 | 60.53 | 86.97 | 74.44 | 86.00 | diff --git a/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_gen.py b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_gen.py new file mode 100644 index 00000000..e2d02a1c --- /dev/null +++ b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_gen.py @@ -0,0 +1,69 @@ +from opencompass.openicl.icl_prompt_template import PromptTemplate +from opencompass.openicl.icl_retriever import FixKRetriever +from opencompass.openicl.icl_inferencer import GenInferencer +from opencompass.openicl.icl_evaluator import AccwithDetailsEvaluator +from opencompass.datasets import MMLUDataset +from opencompass.utils.text_postprocessors import first_option_postprocess + +# 指定只使用生命科学相关的子集 +mmlu_life_science_subsets = [ + 'anatomy', # 解剖学 + 'clinical_knowledge', # 临床知识 + 'professional_medicine', # 专业医学 + 'medical_genetics', # 遗传学 + 'college_medicine', # 大学医学 + 'college_biology', # 大学生物学 +] + +mmlu_reader_cfg = dict( + input_columns=['input', 'A', 'B', 'C', 'D'], + output_column='target', + train_split='dev') + +mmlu_datasets = [] + +for _name in mmlu_life_science_subsets: + _hint = f'There is a single choice question about {_name.replace("_", " ")}. Answer the question by replying A, B, C or D.' + mmlu_infer_cfg = dict( + ice_template=dict( + type=PromptTemplate, + template=dict(round=[ + dict( + role='HUMAN', + prompt=f'{_hint}\nQuestion: {{input}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nAnswer: '), + dict(role='BOT', prompt='{target}\n') + ]), + ), + prompt_template=dict( + type=PromptTemplate, + template=dict( + begin='', + round=[ + dict( + role='HUMAN', + prompt=f'{_hint}\nQuestion: {{input}}\nA. {{A}}\nB. {{B}}\nC. {{C}}\nD. {{D}}\nAnswer: ' + ), + ], + ), + ice_token='', + ), + retriever=dict(type=FixKRetriever, fix_id_list=[0, 1, 2, 3, 4]), + inferencer=dict(type=GenInferencer), + ) + + mmlu_eval_cfg = dict( + evaluator=dict(type=AccwithDetailsEvaluator), + pred_postprocessor=dict(type=first_option_postprocess, options='ABCD')) + + mmlu_datasets.append( + dict( + abbr=f'lukaemon_mmlu_{_name}', + type=MMLUDataset, + path='opencompass/mmlu', + name=_name, + reader_cfg=mmlu_reader_cfg, + infer_cfg=mmlu_infer_cfg, + eval_cfg=mmlu_eval_cfg, + )) + +del _name, _hint diff --git a/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_llmjudge_gen.py b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_llmjudge_gen.py new file mode 100644 index 00000000..05bc2913 --- /dev/null +++ b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_llmjudge_gen.py @@ -0,0 +1,111 @@ +from mmengine.config import read_base +from opencompass.openicl.icl_prompt_template import PromptTemplate +from opencompass.openicl.icl_retriever import ZeroRetriever +from opencompass.openicl.icl_inferencer import GenInferencer +from opencompass.openicl.icl_evaluator import AccEvaluator +from opencompass.datasets import MMLUDataset +from opencompass.utils.text_postprocessors import match_answer_pattern +from opencompass.evaluator import GenericLLMEvaluator +from opencompass.datasets import generic_llmjudge_postprocess + +with read_base(): + from .mmlu_lifescience_sets import mmlu_life_science_subsets +# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader +# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar + +QUERY_TEMPLATE = """ +Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD. + +{input} + +A) {A} +B) {B} +C) {C} +D) {D} +""".strip() + + +GRADER_TEMPLATE = """ + Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly. + + Here are some evaluation criteria: + 1. Please refer to the given standard answer. You don't need to re-generate the answer to the question because the standard answer has been given. You only need to judge whether the candidate's answer is consistent with the standard answer according to the form of the question. Don't try to answer the original question. You can assume that the standard answer is definitely correct. + 2. Because the candidate's answer may be different from the standard answer in the form of expression, before making a judgment, please understand the question and the standard answer first, and then judge whether the candidate's answer is correct, but be careful not to try to answer the original question. + 3. Some answers may contain multiple items, such as multiple-choice questions, multiple-select questions, fill-in-the-blank questions, etc. As long as the answer is the same as the standard answer, it is enough. For multiple-select questions and multiple-blank fill-in-the-blank questions, the candidate needs to answer all the corresponding options or blanks correctly to be considered correct. + 4. Some answers may be expressed in different ways, such as some answers may be a mathematical expression, some answers may be a textual description, as long as the meaning expressed is the same. And some formulas are expressed in different ways, but they are equivalent and correct. + + Please judge whether the following answers are consistent with the standard answer based on the above criteria. Grade the predicted answer of this new question as one of: + A: CORRECT + B: INCORRECT + Just return the letters "A" or "B", with no text around it. + + Here is your task. Simply reply with either CORRECT, INCORRECT. Don't apologize or correct yourself if there was a mistake; we are just trying to grade the answer. + + : {input}\n A) {A}\n B) {B}\n C) {C}\n D) {D}\n\n\n + : \n{target}\n\n\n + : \n{prediction}\n\n\n + Judging the correctness of candidates' answers: +""".strip() + +mmlu_reader_cfg = dict( + input_columns=['input', 'A', 'B', 'C', 'D'], + output_column='target', + train_split='dev', +) + +mmlu_datasets = [] +for name in mmlu_life_science_subsets: + mmlu_infer_cfg = dict( + prompt_template=dict( + type=PromptTemplate, + template=dict( + round=[ + dict(role='HUMAN', prompt=QUERY_TEMPLATE), + ], + ), + ), + retriever=dict(type=ZeroRetriever), + inferencer=dict(type=GenInferencer), + ) + + mmlu_eval_cfg = dict( + evaluator=dict( + type=GenericLLMEvaluator, + prompt_template=dict( + type=PromptTemplate, + template=dict( + begin=[ + dict( + role='SYSTEM', + fallback_role='HUMAN', + prompt="You are a helpful assistant who evaluates the correctness and quality of models' outputs.", + ) + ], + round=[ + dict(role='HUMAN', prompt=GRADER_TEMPLATE), + ], + ), + ), + dataset_cfg=dict( + type=MMLUDataset, + path='opencompass/mmlu', + name=name, + reader_cfg=mmlu_reader_cfg, + ), + judge_cfg=dict(), + dict_postprocessor=dict(type=generic_llmjudge_postprocess), + ), + pred_role='BOT', + ) + mmlu_datasets.append( + dict( + abbr=f'lukaemon_mmlu_{name}', + type=MMLUDataset, + path='opencompass/mmlu', + name=name, + reader_cfg=mmlu_reader_cfg, + infer_cfg=mmlu_infer_cfg, + eval_cfg=mmlu_eval_cfg, + mode='singlescore', + ) + ) diff --git a/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_sets.py b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_sets.py new file mode 100644 index 00000000..7e577759 --- /dev/null +++ b/opencompass/configs/datasets/mmlu_lifescience/mmlu_lifescience_sets.py @@ -0,0 +1,8 @@ +mmlu_life_science_subsets = [ + 'anatomy', # 解剖学 + 'clinical_knowledge', # 临床知识 + 'professional_medicine', # 专业医学 + 'medical_genetics', # 遗传学 + 'college_medicine', # 大学医学 + 'college_biology', # 大学生物学 +] diff --git a/opencompass/datasets/SciEval_lifescience.py b/opencompass/datasets/SciEval_lifescience.py new file mode 100644 index 00000000..af93e496 --- /dev/null +++ b/opencompass/datasets/SciEval_lifescience.py @@ -0,0 +1,62 @@ +import re +from typing import List + +from datasets import Dataset, DatasetDict, load_dataset + +from opencompass.datasets.base import BaseDataset +from opencompass.registry import LOAD_DATASET + +# 预编译的多选题正则，按 PEP-8 每行 < 79 字符 +_PATTERN_MC = ( + r'^(?P.*?)' # 题干 + r'(?:A\.)\s*(?P.*?)\s*' # 选项 A + r'B\.\s*(?P.*?)\s*' # 选项 B + r'C\.\s*(?P.*?)\s*' # 选项 C + r'D\.\s*(?P.*?)' # 选项 D + r'Answer:' # 答案分隔符 +) + + +@LOAD_DATASET.register_module() +class SciEvalDataset(BaseDataset): + """Biology multiple-choice subset of SciEval.""" + + @staticmethod + def load(path: str, name: str, **kwargs) -> DatasetDict: + dataset = DatasetDict() + + for split in ('test', ): + raw_iter = load_dataset( + path, + name=name, + split=split, + streaming=True, + ) + + examples: List[dict] = [] + for ex in raw_iter: + if (ex.get('category') != 'biology' + or ex.get('type') != 'multiple-choice'): + continue + + ans_list = ex.get('answer') or ex.get('answers') or [] + if not ans_list: + continue + target = ans_list[0] + + match = re.search(_PATTERN_MC, ex.get('question', ''), re.S) + if not match: + continue + + examples.append({ + 'input': match.group('stem').strip(), + 'A': match.group('A').strip(), + 'B': match.group('B').strip(), + 'C': match.group('C').strip(), + 'D': match.group('D').strip(), + 'target': target, + }) + + dataset[split] = Dataset.from_list(examples) + + return dataset diff --git a/opencompass/datasets/__init__.py b/opencompass/datasets/__init__.py index b00162d1..4d9628ef 100644 --- a/opencompass/datasets/__init__.py +++ b/opencompass/datasets/__init__.py @@ -99,6 +99,7 @@ from .MedXpertQA import * # noqa: F401, F403 from .mgsm import * # noqa: F401, F403 from .mmlu import * # noqa: F401, F403 from .mmlu_cf import * # noqa: F401, F403 +from .mmlu_lifescience import * # noqa: F401, F403 from .mmlu_pro import * # noqa: F401, F403 from .MMLUArabic import * # noqa: F401, F403 from .mmmlu import * # noqa: F401, F403 @@ -127,6 +128,7 @@ from .ruler import * # noqa: F401, F403 from .safety import * # noqa: F401, F403 from .scibench import ScibenchDataset, scibench_postprocess # noqa: F401, F403 from .scicode import * # noqa: F401, F403 +from .SciEval_lifescience import SciEvalDataset # noqa: F401 from .simpleqa import * # noqa: F401, F403 from .siqa import * # noqa: F401, F403 from .smolinstruct import * # noqa: F401, F403 diff --git a/opencompass/datasets/mmlu_lifescience.py b/opencompass/datasets/mmlu_lifescience.py new file mode 100644 index 00000000..7ccba881 --- /dev/null +++ b/opencompass/datasets/mmlu_lifescience.py @@ -0,0 +1,153 @@ +import csv +import json +import os.path as osp +from os import environ + +from datasets import Dataset, DatasetDict + +from opencompass.registry import LOAD_DATASET +from opencompass.utils import get_data_path + +from .base import BaseDataset + + +@LOAD_DATASET.register_module() +class MMLUDataset(BaseDataset): + + @staticmethod + def load(path: str, name: str, **kwargs): + path = get_data_path(path) + dataset = DatasetDict() + if environ.get('DATASET_SOURCE') == 'ModelScope': + from modelscope import MsDataset + for split in ['dev', 'test']: + # 从 ModelScope 加载数据 + ms_dataset = MsDataset.load(path, + subset_name=name, + split=split) + dataset_list = [] + for line in ms_dataset: + dataset_list.append({ + 'input': line['question'], + 'A': line['choices'][0], + 'B': line['choices'][1], + 'C': line['choices'][2], + 'D': line['choices'][3], + 'target': 'ABCD'[line['answer']], + }) + dataset[split] = Dataset.from_list(dataset_list) + else: + for split in ['dev', 'test']: + raw_data = [] + filename = osp.join(path, split, f'{name}_{split}.csv') + with open(filename, encoding='utf-8') as f: + reader = csv.reader(f) + for row in reader: + assert len(row) == 6 + raw_data.append({ + 'input': row[0], + 'A': row[1], + 'B': row[2], + 'C': row[3], + 'D': row[4], + 'target': row[5], + }) + dataset[split] = Dataset.from_list(raw_data) + return dataset + + +class MMLUDatasetClean(BaseDataset): + + # load the contamination annotations of CEval from + # https://github.com/liyucheng09/Contamination_Detector + @staticmethod + def load_contamination_annotations(path, split='val'): + import requests + + assert split == 'test', 'We only use test set for MMLU' + if environ.get('DATASET_SOURCE') == 'ModelScope': + from modelscope.utils.config_ds import MS_DATASETS_CACHE + annotation_cache_path = osp.join( + MS_DATASETS_CACHE, + f'MMLU_{split}_contamination_annotations.json') + link_of_annotations = 'https://modelscope.cn/datasets/opencompass/Contamination_Detector/resolve/master/mmlu_annotations.json' # noqa + else: + annotation_cache_path = osp.join( + path, split, f'MMLU_{split}_contamination_annotations.json') + link_of_annotations = 'https://github.com/liyucheng09/Contamination_Detector/releases/download/v0.1.1rc2/mmlu_annotations.json' # noqa + + if osp.exists(annotation_cache_path): + with open(annotation_cache_path, 'r') as f: + annotations = json.load(f) + return annotations + + annotations = json.loads(requests.get(link_of_annotations).text) + with open(annotation_cache_path, 'w') as f: + json.dump(annotations, f) + return annotations + + @staticmethod + def load(path: str, name: str): + path = get_data_path(path) + dataset = DatasetDict() + if environ.get('DATASET_SOURCE') == 'ModelScope': + for split in ['dev', 'test']: + from modelscope import MsDataset + + # 从 ModelScope 加载数据 + ms_dataset = MsDataset.load(path, + subset_name=name, + split=split) + if split == 'test': + annotations = \ + MMLUDatasetClean.load_contamination_annotations( + path, split) + dataset_list = [] + for row_index, line in enumerate(ms_dataset): + item = { + 'input': line['question'], + 'A': line['choices'][0], + 'B': line['choices'][1], + 'C': line['choices'][2], + 'D': line['choices'][3], + 'target': 'ABCD'[line['answer']], + } + if split == 'test': + row_id = f'{name} {row_index}' + if row_id in annotations: + is_clean = annotations[row_id][0] + else: + is_clean = 'not labeled' + item['is_clean'] = is_clean + dataset_list.append(item) + dataset[split] = Dataset.from_list(dataset_list) + else: + for split in ['dev', 'test']: + raw_data = [] + filename = osp.join(path, split, f'{name}_{split}.csv') + if split == 'test': + annotations = \ + MMLUDatasetClean.load_contamination_annotations( + path, split) + with open(filename, encoding='utf-8') as f: + reader = csv.reader(f) + for row_index, row in enumerate(reader): + assert len(row) == 6 + item = { + 'input': row[0], + 'A': row[1], + 'B': row[2], + 'C': row[3], + 'D': row[4], + 'target': row[5], + } + if split == 'test': + row_id = f'{name} {row_index}' + if row_id in annotations: + is_clean = annotations[row_id][0] + else: + is_clean = 'not labeled' + item['is_clean'] = is_clean + raw_data.append(item) + dataset[split] = Dataset.from_list(raw_data) + return dataset