revise latest conflict

dataset-index.yml

@@ -611,6 +611,12 @@
     paper: https://dl.acm.org/doi/pdf/10.1145/3580305.3599790
     configpath: opencompass/configs/datasets/humanevalx/humanevalx_gen.py
     configpath_llmjudge: ''
+- humaneval_pro:
+    name: HumanEval Pro
+    category: Code
+    paper: https://arxiv.org/abs/2412.21199
+    configpath: opencompass/configs/datasets/humaneval_pro/humaneval_pro_gen.py
+    configpath_llmjudge: ''
 - hungarian_math:
     name: Hungarian_Math
     category: Math
@@ -695,6 +701,12 @@
     paper: ''
     configpath: opencompass/configs/datasets/mbpp_plus/mbpp_plus_gen.py
     configpath_llmjudge: ''
+- mbpp_pro:
+    name: MBPP Pro
+    category: Code
+    paper: https://arxiv.org/abs/2412.21199
+    configpath: opencompass/configs/datasets/mbpp_pro/mbpp_pro_gen.py
+    configpath_llmjudge: ''
 - mgsm:
     name: MGSM
     category: Language / Math
@@ -1065,6 +1077,12 @@
     paper: https://arxiv.org/pdf/2402.09391
     configpath: opencompass/configs/datasets/SmolInstruct/smolinstruct_gen.py
     configpath_llmjudge: ''
+- SciKnowEval:
+    name: SciKnowEval
+    category: Science
+    paper: https://arxiv.org/abs/2406.09098
+    configpath: opencompass/configs/datasets/SciKnowEval/SciKnowEval_gen_ebe47d.py
+    configpath_llmjudge: opencompass/configs/datasets/SciKnowEval/SciKnowEval_llmjudge_gen_ebe47d.py
 - internsandbox:
     name: InternSandbox
     category: Reasoning/Code/Agent

opencompass/configs/datasets/HLE/hle_biomed_llm_verify_gen_6ff468.py

@@ -0,0 +1,88 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.evaluator import GenericLLMEvaluator
+from opencompass.datasets import generic_llmjudge_postprocess
+from opencompass.datasets import HLEDataset
+
+# ----------------------------- Detailed Config -----------------------------
+
+math_reader_cfg = dict(input_columns=['problem'], output_column='answer')
+
+math_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(
+            round=[
+                dict(role='HUMAN', prompt='{problem}\nRemember to put your final answer within \\boxed{}.'), 
+            ]
+        ),
+    ),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer),
+)
+
+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.
+    5. If the prediction is given with \\boxed{}, please ignore the \\boxed{} and only judge whether the candidate's answer is consistent with the standard answer.
+    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.
+    <Original Question Begin>: \n{problem}\n<Original Question End>\n\n
+    <Gold Target Begin>: \n{answer}\n<Gold Target End>\n\n
+    <Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
+    
+    Judging the correctness of candidates' answers:
+""".strip()
+
+# Evaluation configuration
+math_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=HLEDataset,
+            path='cais/hle',
+            reader_cfg=math_reader_cfg,
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=generic_llmjudge_postprocess),
+    ),
+    pred_role='BOT',
+)
+
+
+hle_datasets = [
+    dict(
+        type=HLEDataset,
+        abbr='hle_llmjudge',
+        path='cais/hle',
+        category='Biology/Medicine',
+        reader_cfg=math_reader_cfg,
+        infer_cfg=math_infer_cfg,
+        eval_cfg=math_eval_cfg,
+    )
+]

opencompass/configs/datasets/SciKnowEval/SciKnowEval_gen_ebe47d.py

@@ -0,0 +1,92 @@
+from opencompass.datasets import SciKnowEvalDataset, SciKnowEvalEvaluator
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+
+ZERO_SHOT_PROMPT = '{q4}'
+
+# Reader configuration
+reader_cfg = dict(
+    input_columns=[
+        'prompt',
+        'question',
+        'choices',
+        'label',
+        'answerKey',
+        'type',
+        'domain',
+        'details',
+        'answer',
+        'q4'
+    ],
+    output_column='answerKey',
+)
+
+# Inference configuration
+infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(
+            round=[
+                dict(
+                    role='HUMAN',
+                    prompt=ZERO_SHOT_PROMPT, # prompt mode: zero-shot
+                ),
+            ],
+        ),
+    ),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer),
+)
+
+# Evaluation configuration
+eval_cfg = dict(
+    evaluator=dict(type=SciKnowEvalEvaluator),
+    pred_role='BOT',
+)
+sciknoweval_dataset_biology = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_biology',
+    path='hicai-zju/SciKnowEval',
+    prompt_mode='zero-shot',
+    subset='biology',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+sciknoweval_dataset_chemistry = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_chemistry',
+    path='hicai-zju/SciKnowEval',
+    subset='chemistry',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+sciknoweval_dataset_material = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_material',
+    path='hicai-zju/SciKnowEval',
+    subset='material',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+sciknoweval_dataset_physics = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_physics',
+    path='hicai-zju/SciKnowEval',
+    prompt_mode='zero-shot',
+    subset='physics',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg,
+)
+
+
+sciknoweval_datasets = [sciknoweval_dataset_biology, sciknoweval_dataset_chemistry, sciknoweval_dataset_physics, sciknoweval_dataset_material]

opencompass/configs/datasets/SciKnowEval/SciKnowEval_llmjudge_gen_ebe47d.py

@@ -0,0 +1,232 @@
+from opencompass.datasets import SciKnowEvalDataset
+from opencompass.datasets import generic_llmjudge_postprocess
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.evaluator import GenericLLMEvaluator
+
+ZERO_SHOT_PROMPT = '{q4}'
+
+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.
+
+    <Original Question Begin>: Q: {q4}\n<Original Question End>\n\n
+    <Gold Target Begin>: \n{answerKey}\n<Gold Target End>\n\n
+    <Predicted Answer Begin>: \n{prediction}\n<Predicted End>\n\n
+    Judging the correctness of candidates' answers:
+""".strip()
+
+
+# Reader configuration
+reader_cfg = dict(
+    input_columns=[
+        'prompt',
+        'question',
+        'choices',
+        'label',
+        'answerKey',
+        'type',
+        'domain',
+        'details',
+        'answer',
+        'q4'
+    ],
+    output_column='answerKey',
+)
+
+# Inference configuration
+infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(
+            round=[
+                dict(
+                    
+                    role='HUMAN',
+                    prompt=ZERO_SHOT_PROMPT, # prompt mode: zero-shot
+                ),
+            ],
+        ),
+    ),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer),
+)
+
+# Evaluation configuration
+eval_cfg_biology = 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=SciKnowEvalDataset,
+            path='hicai-zju/SciKnowEval',
+            prompt_mode='zero-shot',
+            subset='biology',
+            reader_cfg=reader_cfg,
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=generic_llmjudge_postprocess),
+    ),
+)
+
+eval_cfg_chemistry = 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=SciKnowEvalDataset,
+            path='hicai-zju/SciKnowEval',
+            prompt_mode='zero-shot',
+            reader_cfg=reader_cfg,
+            subset='chemistry',
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=generic_llmjudge_postprocess),
+    ),
+)
+
+eval_cfg_material = 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=SciKnowEvalDataset,
+            path='hicai-zju/SciKnowEval',
+            prompt_mode='zero-shot',
+            reader_cfg=reader_cfg,
+            subset='material',
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=generic_llmjudge_postprocess),
+    ),
+)
+
+eval_cfg_physics = 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=SciKnowEvalDataset,
+            path='hicai-zju/SciKnowEval',
+            prompt_mode='zero-shot',
+            reader_cfg=reader_cfg,
+            subset='physics',
+        ),
+        judge_cfg=dict(),
+        dict_postprocessor=dict(type=generic_llmjudge_postprocess),
+    ),
+)
+
+sciknoweval_dataset_biology = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_biology_llmjudge',
+    path='hicai-zju/SciKnowEval',
+    prompt_mode='zero-shot',
+    subset='biology',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg_biology,
+)
+
+sciknoweval_dataset_chemistry = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_chemistry_llmjudge',
+    path='hicai-zju/SciKnowEval',
+    subset='chemistry',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg_chemistry,
+)
+sciknoweval_dataset_material = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_material_llmjudge',
+    path='hicai-zju/SciKnowEval',
+    subset='material',
+    prompt_mode='zero-shot',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg_material,
+)
+
+
+sciknoweval_dataset_physics = dict(
+    type=SciKnowEvalDataset,
+    abbr='sciknoweval_physics_llmjudge',
+    path='hicai-zju/SciKnowEval',
+    prompt_mode='zero-shot',
+    subset='physics',
+    reader_cfg=reader_cfg,
+    infer_cfg=infer_cfg,
+    eval_cfg=eval_cfg_physics,
+)
+sciknoweval_datasets = [sciknoweval_dataset_biology, sciknoweval_dataset_chemistry, sciknoweval_dataset_physics, sciknoweval_dataset_material]

opencompass/configs/datasets/humaneval_pro/README.md

@@ -0,0 +1,17 @@
+# HumanEval pro
+
+## OC results
+
+|           model            |   pass@1 |
+|:--------------------------:|---------:|
+|qwen2.5-coder-7b-instruct-hf|     65   |
+|  qwen2.5-14b-instruct-hf   |     67   |
+|  deepseek-v2-lite-chat-hf  |     35   |
+
+## CodeEval-pro results
+
+|           model            |   pass@1 |
+|:--------------------------:|---------:|
+|qwen2.5-coder-7b-instruct-hf|     65   |
+|  qwen2.5-14b-instruct-hf   |     65   |
+|  deepseek-v2-lite-chat-hf  |     28   |

opencompass/configs/datasets/humaneval_pro/humaneval_pro_gen.py

@@ -0,0 +1,4 @@
+from mmengine.config import read_base
+
+with read_base():
+    from .humaneval_pro_gen_3dc067 import humanevalpro_datasets  # noqa: F401, F403

opencompass/configs/datasets/humaneval_pro/humaneval_pro_gen_3dc067.py

@@ -0,0 +1,46 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.datasets import HumanevalevalProDataset, HumanevalProEvaluator, humaneval_postprocess_v2
+
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+humanevalpro_reader_cfg = dict(
+    input_columns=['raw_problem', 'new_problem'], output_column='test_code')
+
+humanevalpro_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(round=[
+            dict(
+                role='HUMAN',
+                prompt=PROMPT_WRAPPER),
+        ])),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer))
+
+humanevalpro_eval_cfg = dict(
+    evaluator=dict(type=HumanevalProEvaluator,
+                   ip_address='https://opencompass-multiple-evaluator.hf.space')
+)
+
+humanevalpro_datasets = [
+    dict(
+        abbr='humaneval_pro',
+        type=HumanevalevalProDataset,
+        path='opencompass/humaneval_pro',
+        reader_cfg=humanevalpro_reader_cfg,
+        infer_cfg=humanevalpro_infer_cfg,
+        eval_cfg=humanevalpro_eval_cfg,)
+]

opencompass/configs/datasets/humaneval_pro/humaneval_pro_repeat_gen_3dc067.py

@@ -0,0 +1,48 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.datasets import HumanevalevalProDataset, HumanevalProEvaluator, humaneval_postprocess_v2
+
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+humanevalpro_reader_cfg = dict(
+    input_columns=['raw_problem', 'new_problem'], output_column='test_code')
+
+humanevalpro_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(round=[
+            dict(
+                role='HUMAN',
+                prompt=PROMPT_WRAPPER),
+        ])),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer))
+
+humanevalpro_eval_cfg = dict(
+    evaluator=dict(type=HumanevalProEvaluator,
+                   ip_address='https://opencompass-multiple-evaluator.hf.space')
+)
+
+humanevalpro_datasets = [
+    dict(
+        abbr='humaneval_pro',
+        type=HumanevalevalProDataset,
+        path='opencompass/humaneval_pro',
+        reader_cfg=humanevalpro_reader_cfg,
+        infer_cfg=humanevalpro_infer_cfg,
+        eval_cfg=humanevalpro_eval_cfg,
+        n=5,
+        k=3)
+]

opencompass/configs/datasets/mbpp_pro/README.md

@@ -0,0 +1,17 @@
+# MBPP pro
+
+## OC results
+
+|           model            |   pass@1 |
+|:--------------------------:|---------:|
+|qwen2.5-coder-7b-instruct-hf|     66   |
+|  qwen2.5-14b-instruct-hf   |     64   |
+|  deepseek-v2-lite-chat-hf  |     36   |
+
+## CodeEval-pro results
+
+|           model            |   pass@1 |
+|:--------------------------:|---------:|
+|qwen2.5-coder-7b-instruct-hf|     65   |
+|  qwen2.5-14b-instruct-hf   |     65   |
+|  deepseek-v2-lite-chat-hf  |     39   |

opencompass/configs/datasets/mbpp_pro/mbpp_pro_gen.py

@@ -0,0 +1,4 @@
+from mmengine.config import read_base
+
+with read_base():
+    from .mbpp_pro_gen_3dc067 import mbpppro_datasets  # noqa: F401, F403

opencompass/configs/datasets/mbpp_pro/mbpp_pro_gen_3dc067.py

@@ -0,0 +1,46 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.datasets import MBPPProDataset, MBPPProEvaluator
+
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+mbpppro_reader_cfg = dict(
+    input_columns=['raw_problem', 'new_problem'], output_column='test_code')
+
+mbpppro_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(round=[
+            dict(
+                role='HUMAN',
+                prompt=PROMPT_WRAPPER),
+        ])),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer))
+
+mbpppro_eval_cfg = dict(
+    evaluator=dict(type=MBPPProEvaluator, 
+                   ip_address='https://opencompass-multiple-evaluator.hf.space'),
+)
+
+mbpppro_datasets = [
+    dict(
+        abbr='mbpp_pro',
+        type=MBPPProDataset,
+        path='opencompass/mbpp_pro',
+        reader_cfg=mbpppro_reader_cfg,
+        infer_cfg=mbpppro_infer_cfg,
+        eval_cfg=mbpppro_eval_cfg)
+]

opencompass/configs/datasets/mbpp_pro/mbpp_pro_repeat_gen_3dc067.py

@@ -0,0 +1,48 @@
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.datasets import MBPPProDataset, MBPPProEvaluator
+
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+mbpppro_reader_cfg = dict(
+    input_columns=['raw_problem', 'new_problem'], output_column='test_code')
+
+mbpppro_infer_cfg = dict(
+    prompt_template=dict(
+        type=PromptTemplate,
+        template=dict(round=[
+            dict(
+                role='HUMAN',
+                prompt=PROMPT_WRAPPER),
+        ])),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer))
+
+mbpppro_eval_cfg = dict(
+    evaluator=dict(type=MBPPProEvaluator, 
+                   ip_address='https://opencompass-multiple-evaluator.hf.space'),
+)
+
+mbpppro_datasets = [
+    dict(
+        abbr='mbpp_pro',
+        type=MBPPProDataset,
+        path='opencompass/mbpp_pro',
+        reader_cfg=mbpppro_reader_cfg,
+        infer_cfg=mbpppro_infer_cfg,
+        eval_cfg=mbpppro_eval_cfg,
+        n=5,
+        k=3)
+]

opencompass/configs/datasets/multipl_e/multiple_gen.py

@@ -0,0 +1,4 @@
+from mmengine.config import read_base
+
+with read_base():
+    from .multiple_top_ten_gen_f44aaf import multiple_datasets  # noqa: F401, F403

opencompass/configs/datasets/multipl_e/multiple_top_ten_gen_f44aaf.py

@@ -32,7 +32,6 @@ multiple_datasets = [
         type=MultiplEDataset,
         abbr=f'humaneval-multiple-{lang}',
         language=lang,
-        num_repeats=1,
         path='opencompass/multipl_e',
         tag='humaneval',
         reader_cfg=multiple_reader_cfg,
@@ -46,7 +45,6 @@ multiple_datasets += [
         type=MultiplEDataset,
         abbr=f'mbpp-multiple-{lang}',
         language=lang,
-        num_repeats=1,
         path='opencompass/multipl_e',
         tag='mbpp',
         reader_cfg=multiple_reader_cfg,

opencompass/configs/datasets/multipl_e/multiple_top_ten_repeat_gen_0cd6ce.py

@@ -0,0 +1,58 @@
+# Select the 10 most popular programming languages from MultiPL-E to compose the test set.
+
+from opencompass.openicl.icl_prompt_template import PromptTemplate
+from opencompass.openicl.icl_retriever import ZeroRetriever
+from opencompass.openicl.icl_inferencer import GenInferencer
+from opencompass.datasets import MultiplEDataset, MultiplEEvaluator
+
+
+_TOP_TEN_LANGUAGE_ = ['cpp']
+
+multiple_reader_cfg = dict(input_columns=['language', 'prompt'], output_column='tests')
+
+multiple_infer_cfg = dict(
+    prompt_template=dict(type=PromptTemplate, template='Based on the provided {language} code snippet, complete the subsequent content. The initial part of the completed code must match the provided code snippet exactly:\n{prompt}'),
+    retriever=dict(type=ZeroRetriever),
+    inferencer=dict(type=GenInferencer),
+)
+
+multiple_eval_cfg = {
+    lang: dict(
+        evaluator=dict(
+            type=MultiplEEvaluator,
+            language=lang,
+            ip_address='https://opencompass-multiple-evaluator.hf.space',
+        ),
+        pred_role='BOT',
+    ) for lang in _TOP_TEN_LANGUAGE_
+}
+
+multiple_datasets = [
+    dict(
+        type=MultiplEDataset,
+        abbr=f'humaneval-multiple-{lang}',
+        language=lang,
+        path='opencompass/multipl_e',
+        tag='humaneval',
+        reader_cfg=multiple_reader_cfg,
+        infer_cfg=multiple_infer_cfg,
+        eval_cfg=multiple_eval_cfg[lang],
+        n=5,
+        k=3
+    ) for lang in _TOP_TEN_LANGUAGE_
+]
+
+multiple_datasets += [
+    dict(
+        type=MultiplEDataset,
+        abbr=f'mbpp-multiple-{lang}',
+        language=lang,
+        path='opencompass/multipl_e',
+        tag='mbpp',
+        reader_cfg=multiple_reader_cfg,
+        infer_cfg=multiple_infer_cfg,
+        eval_cfg=multiple_eval_cfg[lang],
+        n=5,
+        k=3
+    ) for lang in _TOP_TEN_LANGUAGE_
+]

opencompass/datasets/SciKnowEval.py

@@ -0,0 +1,107 @@
+import re
+
+from datasets import load_dataset
+
+from opencompass.openicl import BaseEvaluator
+from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
+
+from .base import BaseDataset
+
+
+def _parse(item, prompt_mode, discipline):
+    choices = item['choices']
+
+    item['q4'] = f'You are an expert in {discipline}.\n'
+    item['q4'] += item['prompt']['default'] + '\n' + item['question'] + '\n'
+    label_texts = []
+    for label_meta, text_meta in zip(choices['label'], choices['text']):
+        label_texts.append(f'{label_meta}. {text_meta}')
+    item['q4'] += '\n'.join(label_texts)  # noqa: E501, E741, E741
+    item['prompt_mode'] = prompt_mode
+    return item
+
+
+@LOAD_DATASET.register_module()
+class SciKnowEvalDataset(BaseDataset):
+
+    @staticmethod
+    def load(path: str, prompt_mode: str, **kwargs):
+
+        def capitalize_first_letter(s):
+            if not s:  # 检查字符串是否为空
+                return s
+            return s[0].upper() + s[1:]
+
+        subset = kwargs['subset']
+        data_files = {}
+        test_file = f'data/{capitalize_first_letter(subset)}/'
+        test_file += f'sciknoweval_{subset}_test.jsonl'
+        data_files['test'] = test_file
+        dataset = load_dataset(path, data_files=data_files, split='test')
+        # dataset = dataset.select(range(20))
+        if prompt_mode == 'zero-shot':
+            dataset = dataset.map(
+                lambda item: _parse(item, prompt_mode, subset),
+                load_from_cache_file=False)
+        elif prompt_mode == 'few-shot':
+            pass  # TODO: Implement few-shot prompt
+        return dataset
+
+
+class SciKnowEvalEvaluator(BaseEvaluator):
+
+    def score(self, predictions, references, test_set):
+        method = test_set['prompt_mode'][0]
+
+        if len(predictions) != len(references):
+            return {'error': 'preds and refrs have different length'}
+        correct = 0
+        count = 0
+        details = []
+        for idx, (i, j) in enumerate(zip(predictions, references)):
+            i = answer_cleansing(method, i, test_set['choices'][idx]['label'],
+                                 test_set['answerKey'][idx])
+            detail = {'pred': i, 'answer': j, 'correct': False}
+            count += 1
+            if i == j:
+                correct += 1
+                detail['correct'] = True
+            details.append(detail)
+        result = {'accuracy': 100 * correct / count, 'details': details}
+        return result
+
+
+@TEXT_POSTPROCESSORS.register_module()
+def answer_cleansing(
+    method: str,
+    prediction: str,
+    options: list,
+    label: str,
+) -> str:
+    options_str = r'\b(' + '|'.join(options) + r')\b'
+    prediction = re.findall(options_str, prediction)
+
+    if len(prediction) == 0:
+        prediction = []
+    else:
+        # If there is a "label" and its length is 1,
+        # process prediction accordingly
+        if len(label) == 1:
+            if method == 'few-shot':
+                answer_flag = True if len(prediction) > 1 else False
+                # choose the first or last element based on the answer_flag
+                if answer_flag:
+                    prediction = [prediction[0]]
+                else:
+                    prediction = [prediction[-1]]
+            elif method == 'zero-shot':
+                # choose the first element in list
+                prediction = [prediction[0]]
+            else:
+                raise ValueError('Method is not properly defined ...')
+
+            # Remove trailing period if it exists
+            if prediction[0] and prediction[0].endswith('.'):
+                prediction[0] = prediction[0][:-1]
+
+    return prediction[0]

opencompass/datasets/__init__.py

@@ -64,6 +64,7 @@ from .hle import *  # noqa: F401, F403
 from .huggingface import *  # noqa: F401, F403
 from .humaneval import *  # noqa: F401, F403
 from .humaneval_multi import *  # noqa: F401, F403
+from .humaneval_pro import *  # noqa: F401, F403
 from .humanevalx import *  # noqa: F401, F403
 from .hungarian_math import *  # noqa: F401, F403
 from .IFEval.ifeval import IFEvalDataset, IFEvaluator  # noqa: F401, F403
@@ -96,6 +97,7 @@ from .math401 import *  # noqa: F401, F403
 from .math_intern import *  # noqa: F401, F403
 from .mathbench import *  # noqa: F401, F403
 from .mbpp import *  # noqa: F401, F403
+from .mbpp_pro import *  # noqa: F401, F403
 from .medbench import *  # noqa: F401, F403
 from .Medbullets import *  # noqa: F401, F403
 from .MedCalc_Bench import MedCalc_BenchDataset  # noqa: F401
@@ -136,6 +138,7 @@ 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 .SciKnowEval import *  # noqa: F401, F403
 from .simpleqa import *  # noqa: F401, F403
 from .siqa import *  # noqa: F401, F403
 from .smolinstruct import *  # noqa: F401, F403

opencompass/datasets/hle.py

@@ -9,9 +9,12 @@ from .base import BaseDataset
 class HLEDataset(BaseDataset):
 
     @staticmethod
-    def load(path: str):
+    def load(path: str, category: str | None = None):
         dataset = load_dataset(path)
-        dataset['test'] = dataset['test'].filter(lambda x: x['image'] == '')
+        ds = dataset['test'].filter(lambda x: x['image'] == '')
-        dataset['test'] = dataset['test'].rename_column('question', 'problem')
+        if category:
-        dataset['train'] = dataset['test']
+            ds = ds.filter(lambda x: x['category'] == category)
+        ds = ds.rename_column('question', 'problem')
+        dataset['train'] = ds
+        dataset['test'] = ds
         return dataset

opencompass/datasets/humaneval_pro.py

@@ -0,0 +1,81 @@
+# flake8: noqa: E501s
+
+import json
+from typing import Dict, List
+
+from datasets import Dataset
+
+from opencompass.openicl.icl_evaluator.code_evaluator import CodeEvaluator
+from opencompass.utils import get_data_path
+
+from .base import BaseDataset
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+class HumanevalevalProDataset(BaseDataset):
+
+    @staticmethod
+    def load(path, local_mode=False):
+        path = get_data_path(path, local_mode=local_mode)
+        dataset = []
+        with open(path, encoding='utf-8') as f:
+            raw_data = json.load(f)
+            for data in raw_data:
+                dataset.append(data)
+        return Dataset.from_list(dataset)
+
+
+class HumanevalProEvaluator(CodeEvaluator):
+
+    def score(self, predictions: List, references: List,
+              test_set: Dataset) -> Dict:
+        if len(predictions) != len(references):
+            return {
+                'error':
+                'predictions and references have different '
+                f'length. len(predictions): {len(predictions)}, '
+                f'len(references): {len(references)}'
+            }
+
+        test_set = test_set.to_pandas()
+        # Use the first column as the unique identifier
+        test_set_origin = test_set.drop_duplicates(subset=test_set.columns[0])
+
+        # 1. Prepare data for all test cases
+        all_test_cases, prompts = [], []
+        for i in range(len(test_set_origin)):
+            test_case = test_set_origin.iloc[i]
+            completion = predictions[i]
+
+            # Process code completions
+            processed_completion = self._process_completions(completion)
+            code = processed_completion + '\n' + test_case['test_code']
+            sub_data_dict = {
+                'name': int(test_case['id']),
+                'language': self.language,
+                'code': code,
+            }
+            all_test_cases.append(sub_data_dict)
+
+            prompt = PROMPT_WRAPPER.format(
+                raw_problem=test_case['raw_problem'],
+                new_problem=test_case['new_problem'])
+            prompts.append(prompt)
+
+        # 2. Send all test cases to the evaluation service
+        success, outputs, error_message = self._evaluate(all_test_cases)
+        if not success:
+            return {'error': error_message}
+
+        # 3. Process the returned results
+        return self._process_results(outputs, prompts, len(test_set_origin))

opencompass/datasets/mbpp_pro.py

@@ -0,0 +1,81 @@
+# flake8: noqa: E501
+
+import json
+from typing import Dict, List
+
+from datasets import Dataset
+
+from opencompass.openicl.icl_evaluator.code_evaluator import CodeEvaluator
+from opencompass.utils import get_data_path
+
+from .base import BaseDataset
+
+PROMPT_WRAPPER = """You are an exceptionally intelligent coding assistant that consistently delivers accurate and reliable responses to user instructions.
+Write a solution of python file to the following problems, the solution of the second problem requires single or multiple calls to the first solution.
+```python
+{raw_problem}
+{new_problem}
+```
+Please put the two solutions within the Python code block provided below, and make sure that the block contains no other unrelated content:
+```python
+```
+"""
+
+
+class MBPPProDataset(BaseDataset):
+
+    @staticmethod
+    def load(path, local_mode=False):
+        path = get_data_path(path, local_mode=local_mode)
+        print(path)
+        dataset = []
+        with open(path, encoding='utf-8') as f:
+            for line in f:
+                dataset.append(json.loads(line.strip()))
+        return Dataset.from_list(dataset)
+
+
+class MBPPProEvaluator(CodeEvaluator):
+
+    def score(self, predictions: List, references: List,
+              test_set: Dataset) -> Dict:
+        if len(predictions) != len(references):
+            return {
+                'error':
+                'predictions and references have different '
+                f'length. len(predictions): {len(predictions)}, '
+                f'len(references): {len(references)}'
+            }
+
+        test_set = test_set.to_pandas()
+        # Use the first column as the unique identifier
+        test_set_origin = test_set.drop_duplicates(subset=test_set.columns[0])
+
+        # 1. Prepare data for all test cases
+        all_test_cases, prompts = [], []
+        for i in range(len(test_set_origin)):
+            test_case = test_set_origin.iloc[i]
+            completion = predictions[i]
+
+            # Process code completions
+            processed_completion = self._process_completions(completion)
+            code = processed_completion + '\n' + test_case['test_code']
+            sub_data_dict = {
+                'name': int(test_case['id']),
+                'language': self.language,
+                'code': code,
+            }
+            all_test_cases.append(sub_data_dict)
+
+            prompt = PROMPT_WRAPPER.format(
+                raw_problem=test_case['raw_problem'],
+                new_problem=test_case['new_problem'])
+            prompts.append(prompt)
+
+        # 2. Send all test cases to the evaluation service
+        success, outputs, error_message = self._evaluate(all_test_cases)
+        if not success:
+            return {'error': error_message}
+
+        # 3. Process the returned results
+        return self._process_results(outputs, prompts, len(test_set_origin))

opencompass/datasets/multipl_e.py

@@ -1,3 +1,4 @@
+import difflib
 import json
 import os.path as osp
 
@@ -28,7 +29,6 @@ class MultiplEDataset(BaseDataset):
     @staticmethod
     def load(path: str,
              language: str,
-             num_repeats: int = 1,
              tag: str = 'humaneval',
              local_mode: bool = False):
         """Load dataset for pass k mode.
@@ -56,8 +56,7 @@ class MultiplEDataset(BaseDataset):
         dataset = []
         with open(file_path, 'r', encoding='utf-8') as f:
             for line in f:
-                dataset.extend(
+                dataset.append(json.loads(line.strip()))
-                    [json.loads(line.strip()) for _ in range(num_repeats)])
         return Dataset.from_list(dataset)
 
 
@@ -84,20 +83,56 @@ class MultiplEEvaluator(CodeEvaluator):
                 min_stop_index = stop_index
         return decoded_string[:min_stop_index]
 
-    def _process_completions(self, test_case, completions):
+    def _remove_prefix(self,
+                       prompt: str,
+                       completion: str,
+                       threshold: float = 0.95) -> str:
+        """Determine the truncation point in the completion based on the last
+        line of the prompt, remove all content before that line in the
+        completion, and return the completion string after removing the prefix.
+        This is done to convert chatbot-style inference mode to completion
+        mode.
+
+        Args:
+            prompt (str): The prompt text.
+            completion (str): The completion text.
+            threshold (float): Line similarity threshold.
+
+        Returns:
+            str: The completion string after removing the prefix.
+        """
+        prompt_lines = prompt.splitlines()
+        completion_lines = completion.splitlines()
+
+        if not prompt_lines:
+            return completion
+
+        last_prompt_line = prompt_lines[-1]
+        cut_index = -1
+
+        for i, completion_line in enumerate(completion_lines):
+            similarity = difflib.SequenceMatcher(None, last_prompt_line,
+                                                 completion_line).ratio()
+            if similarity >= threshold:
+                cut_index = i
+                break
+
+        if cut_index != -1:
+            return '\n'.join(completion_lines[cut_index + 1:])
+        else:
+            return completion
+
+    def _process_completions(self, test_case, completion):
         """Process completions with a test case.
 
         Args:
-            test_case: A test case.
+            test_case (dict): A test case containing prompt and stop tokens.
-            completions: A list of completions.
+            completion (str): The generated code completion.
         Returns:
-            A list of processed completions.
+            str: Processed code completion.
         """
-        processed_completions = []
+        post_comp = self._extract_code(completion)
-        for comp in completions:
+        post_comp = self._remove_prefix(test_case['prompt'], post_comp)
-            comp = self._extract_code(comp)
+        post_comp = self._stop_at_stop_token(post_comp,
-            post_comp = self._remove_prefix(test_case['prompt'], comp)
+                                             test_case['stop_tokens'])
-            post_comp = self._stop_at_stop_token(post_comp,
+        return post_comp
-                                                 test_case['stop_tokens'])
-            processed_completions.append(post_comp)
-        return processed_completions

opencompass/models/openai_api.py

@@ -25,7 +25,7 @@ OPENAI_API_BASE = os.path.join(
 OPENAISDK_API_BASE = os.environ.get('OPENAI_BASE_URL',
                                     'https://api.openai.com/v1/')
 
-O1_MODEL_LIST = ['o1', 'o3']
+O1_MODEL_LIST = ['o1', 'o3', 'o4']
 
 
 @MODELS.register_module()

opencompass/openicl/icl_evaluator/code_evaluator.py

@@ -1,12 +1,12 @@
 # flake8: noqa: E501
 
-import difflib
 import os
 import re
 import tempfile
 import time
 from typing import Any, Dict, List, Optional, Tuple, Union
 
+import numpy as np
 from datasets import Dataset
 from gradio_client import Client
 
@@ -24,9 +24,9 @@ class CodeEvaluator(BaseEvaluator):
     """
 
     def __init__(self,
-                 language: str,
+                 language: str = 'py',
                  ip_address: str = 'localhost',
-                 retry: int = 3) -> None:
+                 retry: int = 5) -> None:
         """Initialize the CodeEvaluator.
 
         Args:
@@ -71,6 +71,7 @@ class CodeEvaluator(BaseEvaluator):
                 - output (dict/list/str): Evaluation results or error message
         """
         try:
+            import requests
             temp_file_path = None
             # Handle file path input
             if isinstance(input_data, str):
@@ -83,7 +84,15 @@ class CodeEvaluator(BaseEvaluator):
                 input_data = temp_file_path
 
             # Send to evaluation service
-            result = self.client.predict(input_data, api_name='/evaluate')
+            try:
+                result = self.client.predict(input_data, api_name='/evaluate')
+            except Exception as e:
+                # Catch timeout and other exceptions
+                if 'timed out' in str(e).lower() or 'timeout' in str(
+                        e).lower():
+                    return False, f'Request to code eval service timed out: {e}'
+                else:
+                    raise
 
             # Process the result
             if isinstance(result, (dict, list)):
@@ -107,63 +116,16 @@ class CodeEvaluator(BaseEvaluator):
                 except:  # noqa: E722
                     pass
 
-    def _remove_prefix(self,
+    def _process_completions(self, completion: str) -> list:
-                       prompt: str,
+        """Process code completions to extract the relevant code.
-                       completion: str,
-                       threshold: float = 0.95) -> str:
-        """Determine the truncation point in the completion based on the last
-        line of the prompt, remove all content before that line in the
-        completion, and return the completion string after removing the prefix.
-        This is done to convert chatbot-style inference mode to completion
-        mode.
 
         Args:
-            prompt (str): The prompt text.
+            completion (str): Code completion string.
-            completion (str): The completion text.
-            threshold (float): Line similarity threshold.
-
         Returns:
-            str: The completion string after removing the prefix.
+            list: List of processed code completions.
         """
-        prompt_lines = prompt.splitlines()
+        post_comp = self._extract_code(completion)
-        completion_lines = completion.splitlines()
+        return post_comp
-
-        if not prompt_lines:
-            return completion
-
-        last_prompt_line = prompt_lines[-1]
-        cut_index = -1
-
-        for i, completion_line in enumerate(completion_lines):
-            similarity = difflib.SequenceMatcher(None, last_prompt_line,
-                                                 completion_line).ratio()
-            if similarity >= threshold:
-                cut_index = i
-                break
-
-        if cut_index != -1:
-            return '\n'.join(completion_lines[cut_index + 1:])
-        else:
-            return completion
-
-    def _process_completions(self, test_case: dict, completions: list) -> list:
-        """Process code completion list, which typically involves extracting
-        code, removing repetitive prefixes caused by chatbot mode, and other
-        steps to ensure the model-generated code can be compiled successfully.
-
-        Args:
-            test_case (dict): Dictionary containing test case information including:
-            completions (list): List of code completions generated by the model.
-
-        Returns:
-            list: Processed code completion list.
-        """
-        processed_completions = []
-        for comp in completions:
-            comp = self._extract_code(comp)
-            post_comp = self._remove_prefix(test_case['prompt'], comp)
-            processed_completions.append(post_comp)
-        return processed_completions
 
     def _evaluate(
         self, input_data: Union[Dict, List]
@@ -186,7 +148,7 @@ class CodeEvaluator(BaseEvaluator):
             succeed, output = self._code_eval_service(input_data)
             if not succeed:
                 num_retry += 1
-                time.sleep(10)
+                time.sleep(30)
             else:
                 break
 
@@ -195,6 +157,31 @@ class CodeEvaluator(BaseEvaluator):
 
         return True, output, None
 
+    def _process_results(self, outputs: List, prompts: List,
+                         total_count: int) -> Dict:
+        """Process the evaluation results.
+        Args:
+            outputs (list): List of evaluation results for each test case.
+            prompts (list): List of prompts used for each test case.
+            total_count (int): Total number of test cases.
+        Returns:
+            dict: Processed results including:
+                - pass@1: Percentage of test cases passed
+                - details: Detailed results for each test case
+        """
+        details = []
+        correct = 0
+        for output, prompt in zip(outputs, prompts):
+            output['prompt'] = prompt
+            if output.get('status') == 'OK':
+                output['correct'] = True
+                correct += 1
+            else:
+                output['correct'] = False
+            details.append(output)
+
+        return {f'pass@1': 100 * correct / total_count, 'details': details}
+
     def score(self, predictions: List, references: List,
               test_set: Dataset) -> Dict:
         """Score code generation predictions against references.
@@ -221,28 +208,25 @@ class CodeEvaluator(BaseEvaluator):
         test_set = test_set.to_pandas()
         # Use the first column as the unique identifier
         test_set_origin = test_set.drop_duplicates(subset=test_set.columns[0])
-        num_repeats = int(len(test_set) / len(test_set_origin))
 
         # 1. Prepare data for all test cases
-        all_test_cases = []
+        all_test_cases, prompts = [], []
         for i in range(len(test_set_origin)):
             test_case = test_set_origin.iloc[i]
-            completions = predictions[i * num_repeats:(i + 1) * num_repeats]
+            completion = predictions[i]
 
             # Process code completions
-            processed_completions = self._process_completions(
+            processed_completion = self._process_completions(
-                test_case, completions)
+                test_case, completion)
-
+            code = test_case[
-            result_dict = {
+                'prompt'] + processed_completion + '\n' + test_case['tests']
+            sub_data_dict = {
                 'name': test_case['name'],
                 'language': test_case['language'],
-                'prompt': test_case['prompt'],
+                'code': code
-                'tests': test_case['tests'],
-                'processed_completions': processed_completions,
-                'completions': completions
             }
-
+            all_test_cases.append(sub_data_dict)
-            all_test_cases.append(result_dict)
+            prompts.append(test_case['prompt'])
 
         # 2. Send all test cases to the evaluation service
         success, outputs, error_message = self._evaluate(all_test_cases)
@@ -250,18 +234,4 @@ class CodeEvaluator(BaseEvaluator):
             return {'error': error_message}
 
         # 3. Process the returned results
-        details = []
+        return self._process_results(outputs, prompts, len(test_set_origin))
-        correct = 0
-        for output in outputs:
-            if output.get('status') == 'OK':
-                output['correct'] = True
-                correct += 1
-            else:
-                output['correct'] = False
-
-            details.append(output)
-
-        return {
-            f'pass@{num_repeats}': 100 * correct / len(test_set_origin),
-            'details': details
-        }

opencompass/utils/datasets_info.py

@@ -451,6 +451,16 @@ DATASETS_MAPPING = {
         "hf_id": "",
         "local": "./data/nejmaibench/NEJM_All_Questions_And_Answers.csv",
     },
+    "opencompass/humaneval_pro": {
+        "ms_id": "",
+        "hf_id": "",
+        "local": "./data/humaneval_pro/humaneval_pro.json",
+    },
+    "opencompass/mbpp_pro": {
+        "ms_id": "",
+        "hf_id": "",
+        "local": "./data/mbpp_pro/mbpp_pro.json",
+    },
     "opencompass/medbullets": {
         "ms_id": "",
         "hf_id": "",
@@ -813,6 +823,13 @@ DATASETS_URL = {
         "url":
         "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/nejmaibench.zip",
         "md5": "e6082cae3596b3ebea73e23ba445b99e"
-    }
+    },
-    
+    "humaneval_pro": {
+        "url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/humaneval_pro.zip",
+        "md5": "4c6fe556e84e905e4f0902d699e46de5",
+    },
+    "mbpp_pro": {
+        "url": "http://opencompass.oss-cn-shanghai.aliyuncs.com/datasets/data/mbpp_pro.zip",
+        "md5": "eac330b8a0a8687f006265c9383503ce",
+    },
 }