evalscope 1.0.2__py3-none-any.whl → 1.1.0__py3-none-any.whl

evalscope/metrics/metric.py

@@ -1,3 +1,4 @@
+import json
 from collections import defaultdict
 from typing import List
 
@@ -100,6 +101,56 @@ class MultiChoiceAcc(Metric):
         return res
 
 
+@register_metric(name='anls')
+class ANLS(Metric):
+
+    def __init__(self, thresh_hold=0.5):
+        self.thresh_hold = thresh_hold
+
+    def apply(self, predictions, references):
+        """
+        Calculate ANLS (Average Normalized Levenshtein Similarity) for a list of predictions and references.
+        This implementation is adapted from
+        https://github.com/QwenLM/Qwen-VL/blob/master/eval_mm/infographicsvqa_eval.py
+
+        Args:
+            references (List[str]): List of correct answers. Each answer can be a string of json.
+            predictions (List[str]): List of predicted answers.
+        """
+        from .metrics import levenshtein_distance
+
+        res = []
+        # Unwrap predictions if it's a nested list
+        for prediction, reference in zip(predictions, references):
+            # Parse the reference which is a json string
+            try:
+                answer = json.loads(reference)
+            except json.JSONDecodeError:
+                answer = reference
+            if isinstance(answer, str):
+                answer = [answer]
+            assert isinstance(answer, list), 'The reference answer should be a list of answers.'
+
+            # Calculate ANLS for each reference answer
+            values = []
+            for ans in answer:
+                # preprocess both the answers - gt and prediction
+                gt_answer = ' '.join(ans.strip().lower().split())
+                det_answer = ' '.join(prediction.strip().lower().split())
+
+                dist = levenshtein_distance(gt_answer, det_answer)
+                length = max(len(ans.upper()), len(prediction.upper()))
+                values.append(0.0 if length == 0 else float(dist) / float(length))
+
+            question_result = 0.0
+            if values:
+                question_result = 1 - min(values)
+                if question_result < self.thresh_hold:
+                    question_result = 0.0
+            res.append(question_result)
+        return res
+
+
 # ##################
 # T2I Metrics ######
 ####################

evalscope/metrics/metrics.py

@@ -467,3 +467,19 @@ def calculate_pass_at_k(
         num_samples_it = iter(num_samples)
 
     return np.array([estimator(int(n), int(c), k) for n, c in zip(num_samples_it, num_correct)])
+
+
+def levenshtein_distance(s1, s2):
+    if len(s1) > len(s2):
+        s1, s2 = s2, s1
+
+    distances = range(len(s1) + 1)
+    for i2, c2 in enumerate(s2):
+        distances_ = [i2 + 1]
+        for i1, c1 in enumerate(s1):
+            if c1 == c2:
+                distances_.append(distances[i1])
+            else:
+                distances_.append(1 + min((distances[i1], distances[i1 + 1], distances_[-1])))
+        distances = distances_
+    return distances[-1]

evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py

@@ -30,13 +30,9 @@ from transformers.modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from transformers.modeling_utils import (
-    PreTrainedModel,
-    apply_chunking_to_forward,
-    find_pruneable_heads_and_indices,
-    prune_linear_layer,
-)
+from transformers.modeling_utils import PreTrainedModel
 from transformers.models.bert.configuration_bert import BertConfig
+from transformers.pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
 from transformers.utils import logging
 from typing import Any, Dict, Optional, Tuple
 

evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py

@@ -14,13 +14,9 @@ from transformers.modeling_outputs import (
     BaseModelOutputWithPastAndCrossAttentions,
     BaseModelOutputWithPoolingAndCrossAttentions,
 )
-from transformers.modeling_utils import (
-    PreTrainedModel,
-    apply_chunking_to_forward,
-    find_pruneable_heads_and_indices,
-    prune_linear_layer,
-)
+from transformers.modeling_utils import PreTrainedModel
 from transformers.models.bert.configuration_bert import BertConfig
+from transformers.pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
 from transformers.utils import logging
 from typing import Tuple
 

evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py

@@ -31,13 +31,9 @@ from transformers.modeling_outputs import (
     SequenceClassifierOutput,
     TokenClassifierOutput,
 )
-from transformers.modeling_utils import (
-    PreTrainedModel,
-    apply_chunking_to_forward,
-    find_pruneable_heads_and_indices,
-    prune_linear_layer,
-)
+from transformers.modeling_utils import PreTrainedModel
 from transformers.models.bert.configuration_bert import BertConfig
+from transformers.pytorch_utils import apply_chunking_to_forward, find_pruneable_heads_and_indices, prune_linear_layer
 from transformers.utils import logging
 from typing import Optional, Tuple
 

evalscope/report/__init__.py

@@ -4,7 +4,13 @@ from typing import TYPE_CHECKING
 from evalscope.utils.import_utils import _LazyModule
 
 if TYPE_CHECKING:
-    from .combinator import gen_table, get_data_frame, get_report_list
+    from .combinator import (
+        gen_table,
+        get_data_frame,
+        get_report_list,
+        unweighted_average_from_subsets,
+        weighted_average_from_subsets,
+    )
     from .generator import ReportGenerator
     from .report import Category, Report, ReportKey, Subset
 
@@ -14,6 +20,8 @@ else:
             'gen_table',
             'get_data_frame',
             'get_report_list',
+            'weighted_average_from_subsets',
+            'unweighted_average_from_subsets',
         ],
         'generator': [
             'ReportGenerator',

evalscope/report/combinator.py

@@ -4,9 +4,9 @@ import glob
 import os
 import pandas as pd
 from tabulate import tabulate
-from typing import List, Tuple
+from typing import Dict, List, Tuple, Union
 
-from evalscope.report.report import Report
+from evalscope.report.report import Report, Subset
 from evalscope.utils.logger import get_logger
 
 logger = get_logger()
@@ -86,3 +86,53 @@ def gen_table(
         add_overall_metric=add_overall_metric
     )
     return tabulate(table, headers=table.columns, tablefmt='grid', showindex=False)
+
+
+def weighted_average_from_subsets(
+    subset_names: List[str], subset_dict: Dict[str, Subset], new_name: str = ''
+) -> Subset:
+    """Calculate weighted average for given subsets.
+
+    Args:
+        subset_names (List[str]): List of subset names to include in the average.
+        subset_dict (Dict[str, Subset]): Dictionary mapping subset names to Subset objects.
+        new_name (str): Name for the resulting Subset object.
+
+    Returns:
+        Subset: A new Subset object with weighted average score
+    """
+    total_score = 0
+    total_count = 0
+    for name in subset_names:
+        if name in subset_dict:
+            subset = subset_dict[name]
+            total_score += subset.score * subset.num
+            total_count += subset.num
+
+    weighted_avg = total_score / total_count if total_count > 0 else 0
+    return Subset(name=new_name, score=weighted_avg, num=total_count)
+
+
+def unweighted_average_from_subsets(
+    subset_names: List[str], subset_dict: Dict[str, Subset], new_name: str = ''
+) -> Subset:
+    """Calculate unweighted average for given subsets.
+
+    Args:
+        subset_names (List[str]): List of subset names to include in the average.
+        subset_dict (Dict[str, Subset]): Dictionary mapping subset names to Subset objects.
+        new_name (str): Name for the resulting Subset object.
+
+    Returns:
+        Subset: A new Subset object with unweighted average score
+    """
+    scores = []
+    total_count = 0
+    for name in subset_names:
+        if name in subset_dict:
+            subset = subset_dict[name]
+            scores.append(subset.score)
+            total_count += subset.num
+
+    unweighted_avg = sum(scores) / len(scores) if scores else 0
+    return Subset(name=new_name, score=unweighted_avg, num=total_count)

evalscope/utils/json_schema.py

@@ -59,18 +59,20 @@ class JSONSchema(BaseModel):
     required: Optional[List[str]] = Field(default=None)
     """Required fields for object parameters."""
 
-    @field_validator('type')
-    def validate_type(cls, v: Optional[str]) -> Optional[JSONType]:
-        return python_type_to_json_type(v)
-
     @model_validator(mode='before')
     def convert_type_before_validation(cls, values):
         values = deepcopy(values)
 
         def recursive_convert_type(obj):
             if isinstance(obj, dict):
-                if 'type' in obj:
-                    obj['type'] = python_type_to_json_type(obj['type'])
+                # Convert 'type' field if it's a string
+                if 'type' in obj and isinstance(obj['type'], str):
+                    try:
+                        obj['type'] = python_type_to_json_type(obj['type'])
+                    except ValueError:
+                        # If conversion fails, leave it as is
+                        pass
+                # Recursively process nested structures
                 for k, v in obj.items():
                     obj[k] = recursive_convert_type(v)
             elif isinstance(obj, list):

evalscope/utils/multi_choices.py

@@ -81,12 +81,27 @@ def answer_options(choices: Choices) -> str:
     return '\n'.join([f'{answer_character(i)}) {choices[j].value}' for i, j in enumerate(indexes)])
 
 
+def format_letter_choices(choices: Union[Choices, List[str]]) -> str:
+    """
+    Returns the `choices` formatted as a letter list, e.g.:
+
+    ["choice 1", "choice 2", "choice 3"] ->
+        "A,B,C"
+    """
+    if isinstance(choices, list):
+        choices = Choices(choices)
+
+    indexes = list(range(len(choices)))
+
+    return ','.join([f'{answer_character(i)}' for i in indexes])
+
+
 def prompt(question: str, choices: Union[Choices, List[str]], template: str, fewshot: Optional[str] = None) -> str:
     if isinstance(choices, list):
         choices = Choices(choices)
 
     choices_text = answer_options(choices)
-    letters = ','.join(answer_character(i) for i in range(len(choices)))
+    letters = format_letter_choices(choices)
     if not fewshot:
         return template.format(
             choices=choices_text,

evalscope/version.py

@@ -1,4 +1,4 @@
 # Copyright (c) Alibaba, Inc. and its affiliates.
 
-__version__ = '1.0.2'
-__release_datetime__ = '2025-09-23 18:00:00'
+__version__ = '1.1.0'
+__release_datetime__ = '2025-10-14 14:00:00'

{evalscope-1.0.2.dist-info → evalscope-1.1.0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 1.0.2
+Version: 1.1.0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
-Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
 Author-email: contact@modelscope.cn
 License: Apache License 2.0
+Project-URL: Homepage, https://github.com/modelscope/evalscope
 Keywords: python,llm,evaluation
 Classifier: Development Status :: 4 - Beta
 Classifier: Operating System :: OS Independent
@@ -14,6 +14,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
@@ -56,35 +57,6 @@ Requires-Dist: peft>=0.17; extra == "aigc"
 Requires-Dist: torch; extra == "aigc"
 Requires-Dist: torchvision; extra == "aigc"
 Provides-Extra: all
-Requires-Dist: colorlog; extra == "all"
-Requires-Dist: datasets==3.6.0; extra == "all"
-Requires-Dist: docstring-parser; extra == "all"
-Requires-Dist: dotenv; extra == "all"
-Requires-Dist: jieba; extra == "all"
-Requires-Dist: jsonlines; extra == "all"
-Requires-Dist: langdetect; extra == "all"
-Requires-Dist: latex2sympy2-extended[antlr4_9_3]; extra == "all"
-Requires-Dist: matplotlib; extra == "all"
-Requires-Dist: modelscope[framework]>=1.27; extra == "all"
-Requires-Dist: nltk>=3.9; extra == "all"
-Requires-Dist: openai; extra == "all"
-Requires-Dist: overrides; extra == "all"
-Requires-Dist: pandas; extra == "all"
-Requires-Dist: pillow; extra == "all"
-Requires-Dist: pydantic; extra == "all"
-Requires-Dist: pyyaml>=5.1; extra == "all"
-Requires-Dist: requests; extra == "all"
-Requires-Dist: rich; extra == "all"
-Requires-Dist: rouge-chinese; extra == "all"
-Requires-Dist: rouge-score>=0.1.0; extra == "all"
-Requires-Dist: sacrebleu; extra == "all"
-Requires-Dist: scikit-learn; extra == "all"
-Requires-Dist: seaborn; extra == "all"
-Requires-Dist: sympy; extra == "all"
-Requires-Dist: tabulate; extra == "all"
-Requires-Dist: tqdm; extra == "all"
-Requires-Dist: transformers>=4.33; extra == "all"
-Requires-Dist: word2number; extra == "all"
 Requires-Dist: ms-opencompass>=0.1.6; extra == "all"
 Requires-Dist: ms-vlmeval>=0.0.17; extra == "all"
 Requires-Dist: langchain<0.4.0,>=0.3.0; extra == "all"
@@ -99,6 +71,7 @@ Requires-Dist: aiohttp; extra == "all"
 Requires-Dist: fastapi; extra == "all"
 Requires-Dist: jinja2; extra == "all"
 Requires-Dist: numpy; extra == "all"
+Requires-Dist: rich; extra == "all"
 Requires-Dist: sse-starlette; extra == "all"
 Requires-Dist: transformers; extra == "all"
 Requires-Dist: uvicorn; extra == "all"
@@ -266,7 +239,8 @@ Please scan the QR code below to join our community groups:
 > **Version 1.0 Refactoring**
 >
 > Version 1.0 introduces a major overhaul of the evaluation framework, establishing a new, more modular and extensible API layer under `evalscope/api`. Key improvements include standardized data models for benchmarks, samples, and results; a registry-based design for components such as benchmarks and metrics; and a rewritten core evaluator that orchestrates the new architecture. Existing benchmark adapters have been migrated to this API, resulting in cleaner, more consistent, and easier-to-maintain implementations.
-
+- 🔥 **[2025.10.14]** Added support for OCRBench, OCRBench-v2, DocVQA, InfoVQA, ChartQA, and BLINK multimodal image-text evaluation benchmarks.
+- 🔥 **[2025.09.22]** Code evaluation benchmarks (HumanEval, LiveCodeBench) now support running in a sandbox environment. To use this feature, please install [ms-enclave](https://github.com/modelscope/ms-enclave) first.
 - 🔥 **[2025.09.19]** Added support for multimodal image-text evaluation benchmarks including RealWorldQA, AI2D, MMStar, MMBench, and OmniBench, as well as pure text evaluation benchmarks such as Multi-IF, HealthBench, and AMC.
 - 🔥 **[2025.09.05]** Added support for vision-language multimodal model evaluation tasks, such as MathVista and MMMU. For more supported datasets, please [refer to the documentation](https://evalscope.readthedocs.io/zh-cn/latest/get_started/supported_dataset/vlm.html).
 - 🔥 **[2025.09.04]** Added support for image editing task evaluation, including the [GEdit-Bench](https://modelscope.cn/datasets/stepfun-ai/GEdit-Bench) benchmark. For usage instructions, refer to the [documentation](https://evalscope.readthedocs.io/en/latest/user_guides/aigc/image_edit.html).

{evalscope-1.0.2.dist-info → evalscope-1.1.0.dist-info}/RECORD

@@ -4,14 +4,14 @@ evalscope/config.py,sha256=S2N11-AxQkT7lVffpjXdtpT4QpnSP6th-c8I-501mwM,11507
 evalscope/constants.py,sha256=W3E4Jp-x6qxvPOYtU9bNlzlERFvSAA_3F007apIwUlU,3601
 evalscope/run.py,sha256=A9_7pR3FiA-It46A3Mqk7ce6fQy548p0ux2QUugj2hI,6531
 evalscope/summarizer.py,sha256=HUDJ1zKi22uNst3AUfX67Z0sHzeZy-4S8sYyvxJnBzc,5901
-evalscope/version.py,sha256=H_zHGJkiB6equdW6Jo4F_hhdLYKZqriowav05O5_CeY,118
+evalscope/version.py,sha256=hqGJMtjd3F6yPJucqhuYtXuGYSumthFmroHsUTY761Y,118
 evalscope/api/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/api/registry.py,sha256=Qk0KMGDbt-iI0-OfoJZbOtxt76qreAVWh36HOoQAKM4,5448
 evalscope/api/benchmark/__init__.py,sha256=9xcTxpcQ6HhZ0QDwEIZhAT5IjybzaJ60VGLcmaFE5dU,188
 evalscope/api/benchmark/benchmark.py,sha256=gqAM81SeGb_Q0rA6Q-LFpnNkOUiwOj43aRWECtCxAOE,10832
 evalscope/api/benchmark/meta.py,sha256=N4u8NQjkjIw-xaf6KFnb6C8JDKB0DLbsXyXblDqIpvE,4304
 evalscope/api/benchmark/adapters/__init__.py,sha256=uLt_GiU4s-_6Rjgmr4OUTtE7dvEX-ZIQ403fd6oNuxA,264
-evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=WS4Pm0pk51Se196Ho31FmOqGyOajTtUGbbjWD9U7UwU,28064
+evalscope/api/benchmark/adapters/default_data_adapter.py,sha256=RWDweSmXKGv5hPPjeV4VF76gbKqYJEsab_lQYGUM2PA,28785
 evalscope/api/benchmark/adapters/image_edit_adapter.py,sha256=06V-_A8RKuMNYMt7-vaXn2qBa9LIZgfFO_6PUuhAkh0,3052
 evalscope/api/benchmark/adapters/multi_choice_adapter.py,sha256=auqLNvF50Or9bo3LOmQLXHfFaTTCTqvQzZog3glInng,3062
 evalscope/api/benchmark/adapters/text2image_adapter.py,sha256=jO64hwjQexIv-MTyHH0Ffp_6p--9TKufOmX_U39mAnE,6385
@@ -50,15 +50,15 @@ evalscope/app/arguments.py,sha256=1wHTLeFx1G94cKXYOeOVe_wTiOY2D929UctIRGOtRaQ,69
 evalscope/app/constants.py,sha256=oG6tZ618zJcCnwZ5THnYL0gWTPDb5XKrnmdrWxY3Z4Q,385
 evalscope/app/ui/__init__.py,sha256=IBxyQ2H-kSHoHJmXWDR8QMermvsMbiu673PQbXP_FnE,616
 evalscope/app/ui/app_ui.py,sha256=wLrQ4VM7BnzvaYmPAk8NH9t5BaWooHFJcgmAOOd2I1w,2032
-evalscope/app/ui/multi_model.py,sha256=fO8z-ZFucWtgaKmuQ50AkUp4BoYOFqOkxeTBUUAK0bM,15122
+evalscope/app/ui/multi_model.py,sha256=mvMgpgiJGRrNRtReFcD_PiLatq-81zp65Vb3JYUP3PE,15356
 evalscope/app/ui/sidebar.py,sha256=JA0QbG2iPStK-lFy6x_AjOHlQdesmgXoS0OYJUJ_Wyg,1339
-evalscope/app/ui/single_model.py,sha256=1rgYrJOO75fJG2pa74tzEocO_91jXOAKFQAUViBcYFk,9459
+evalscope/app/ui/single_model.py,sha256=zFt1uDYrcgNJ7e_YLigrs6IXT3jyGMVn-7rv4CHAZvE,9741
 evalscope/app/ui/visualization.py,sha256=jXFX_-7woQkcAiQkPAIRwVv1kdRdXonn9IvmB8yzPDU,1102
-evalscope/app/utils/data_utils.py,sha256=m7Z0Us_josUFseI8VJpIp8QaYeLnu91E2HCZ8WSB07E,7396
+evalscope/app/utils/data_utils.py,sha256=GYOfkh0NoueeX3od-L852Q9C9SSkEFlW_40wjPa5b9w,7470
 evalscope/app/utils/env_utils.py,sha256=2pmz4uNun-XNP6TqM6Oe576XopweEClhBaIdWO--kd0,382
 evalscope/app/utils/localization.py,sha256=rWEviBmcnhIpAA-cG8djbbUA6p1Y358c0dxge5Pqi1U,6131
 evalscope/app/utils/text_utils.py,sha256=-K-hRPMZ29Yqjhzd-391gPaD4B4wUuIg71PfbLnGJ38,3754
-evalscope/app/utils/visualization.py,sha256=dwEXbGfY7vFysnL0HmrHS2BEWaJkg-dZ9ayDlRhdvv4,3559
+evalscope/app/utils/visualization.py,sha256=lycwcr-kFT2FKVw6iWMh3iD_n4dqpWVzhXMLDnkN8QY,3563
 evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/backend/base.py,sha256=qYu8Shokrtrx-N6T_BAJk_6OCpovUBYuN0p3wngt-dw,1030
 evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
@@ -109,7 +109,7 @@ evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4ty
 evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=jlwM13Ty-Ax6AeMsNlo9xIBupNFgnceYuXtCmh0hNTQ,6160
 evalscope/benchmarks/__init__.py,sha256=WHR4ej9Tqa2N9CyIaUWXS8EnHZtcujaNeg9hf8GT31Y,1182
 evalscope/benchmarks/ai2d/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/ai2d/ai2d_adapter.py,sha256=3GBNV4cNv9bBLJRdG_uA9qNhuN6qAEutHl8d-rsFpFU,2018
+evalscope/benchmarks/ai2d/ai2d_adapter.py,sha256=qnQT2E0ZG8g4noOafu-QvBOKm-zEJ5X08QHw3ekNa4w,2473
 evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aime/aime24_adapter.py,sha256=HTlriHoHzlm1Rf3KAiGRLs8sx6Gyf6s7RGtOjk_hGS4,1767
 evalscope/benchmarks/aime/aime25_adapter.py,sha256=ZOE_6Zhg1MatWJSu2Zq372nKUODYtNFZimS1MJRFz5A,1591
@@ -152,10 +152,15 @@ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt
 evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt,sha256=s_x6u5MLeKpuAHZj3GNQqY1I8vWqQIfJasOp9XcM7Ck,2945
 evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt,sha256=qfTZafCzNiz9ULBaDlfy_LISL617NyH5Nc0-nO0K0LE,2164
 evalscope/benchmarks/bfcl/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/bfcl/bfcl_adapter.py,sha256=WzpL7XWDdx-EvbLluIOiMlADTO42CYs0IwQFvIfhTI0,18402
+evalscope/benchmarks/bfcl/bfcl_adapter.py,sha256=ZmwGylqXCAcpJ8glQmj7HkDa8OqE9KODiHvWelTGLIo,17033
 evalscope/benchmarks/bfcl/generation.py,sha256=c6lNjo-VTSUrVg-pqyPSucrbCKBOdBSyN0aR5AAtE4A,8701
+evalscope/benchmarks/blink/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/blink/blink_adapter.py,sha256=ocQKsDGwnUAg2si2p7tqIGeH3PKPqTSByjbt7ceraRo,2642
 evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/ceval/ceval_adapter.py,sha256=4FLPgY-UtqINafnNxfOsE9AwS6GFXFCUGOBI-4EZUGk,8503
+evalscope/benchmarks/chartqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/chartqa/chartqa_adapter.py,sha256=DA1kthMUvn4_GUfdRfuR-au3RkhE3WKPnR_f8nlhd4c,2813
+evalscope/benchmarks/chartqa/utils.py,sha256=Ta9ZUMpIqzrAszju7_WOMBAlilH1Tx6TCheVpjrZJJI,1672
 evalscope/benchmarks/chinese_simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=OWzRlSGswV24V-heLqqo7GQzpJp01TZ0DhFHq0iUP9A,8238
 evalscope/benchmarks/cmmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -167,6 +172,8 @@ evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=eetF21dN5
 evalscope/benchmarks/docmath/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/docmath/docmath_adapter.py,sha256=-mel6hA-x_e7fV0uOHdX5BpoQEVyQ5VqwIwEqSNDpnc,4623
 evalscope/benchmarks/docmath/utils.py,sha256=d6Yjoa5q91kjr1SdVPVBndzDaUzMlO_GfEqMtUXXr0s,7707
+evalscope/benchmarks/docvqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/docvqa/docvqa_adapter.py,sha256=xGaayycILYoLd8r6wLLppDbU6Z1FdafbYFyjLHaftAA,2882
 evalscope/benchmarks/drop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/drop/drop_adapter.py,sha256=Jbbr5O_Y5LI_vT_RskRQVKxGkiIraX_uXP7fYaZ5eZs,9995
 evalscope/benchmarks/drop/utils.py,sha256=Z9PHrNnRfGqFHCLONg5SWKARp1eTJlHFc_bU46t_YrM,1344
@@ -175,7 +182,7 @@ evalscope/benchmarks/frames/frames_adapter.py,sha256=w1kRya7w5omt95HHE6AzbzYVhyT
 evalscope/benchmarks/frames/utils.py,sha256=gULWM6Rwv5bTSSWcDYp-iSIoWj8r5VtbQakhRzHJq8A,1172
 evalscope/benchmarks/general_arena/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/general_arena/general_arena_adapter.py,sha256=DzJaokqZwR2L8HDiahss8EbQ3vcsMXkzkMghxU-uAOo,21639
-evalscope/benchmarks/general_arena/utils.py,sha256=zS4l1RKwvl0Z9Mk7kth9WVQGHTgE_aNDZa_XNy9tGyM,6874
+evalscope/benchmarks/general_arena/utils.py,sha256=p6pZfvdNCMOU_vWHm_DYU57Sa2WTDdFOkVBubblCRN4,6912
 evalscope/benchmarks/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=7VKg_EzXkRvoWpR7h8qB4sVVb1eZHCGcPk-X_NMS5tE,2062
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -191,7 +198,7 @@ evalscope/benchmarks/healthbench/utils.py,sha256=M8SnOEhlqXWm03CFE6CAtbMiu6MqdGg
 evalscope/benchmarks/hellaswag/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=tAe63NfV5ljUm1f4RTSFxWOVKBUhk3Cc0EGzF5uYLK4,2041
 evalscope/benchmarks/hle/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/hle/hle_adapter.py,sha256=4YVmETL9mEiLxF4vWRjePLyFaxelax6nOaqoAH5ZxmU,6389
+evalscope/benchmarks/hle/hle_adapter.py,sha256=kJP7bzIDbr82GKi0FTy2zf_j1UWNBfuXYzokYJ-S9WE,6410
 evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=uLs3UHSALS3YHt0qzBismrIqdEUgbEalQbjC0CU7ym4,4085
 evalscope/benchmarks/humaneval/utils.py,sha256=rPnc_JuSjNg9aV7UMUwsLrDlm-ufj64GNIBCWBeuRcM,6517
@@ -206,6 +213,8 @@ evalscope/benchmarks/image_edit/gedit/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCe
 evalscope/benchmarks/image_edit/gedit/gedit_adapter.py,sha256=a6hhRbnGCvMEMsbnSbczjXd4vHfMVEnFfP459FCF_Mc,5250
 evalscope/benchmarks/image_edit/gedit/utils.py,sha256=UN0z9Dafs8d8lEXqxin321d8smiS3H9p3gyLkZFPFNg,14735
 evalscope/benchmarks/image_edit/gedit/vie_prompts.py,sha256=qVXWQyVUwZxEasDjVmYBk30_JI4gnvHacMOmMsA4wcI,22056
+evalscope/benchmarks/infovqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/infovqa/infovqa_adapter.py,sha256=3m_EvfRZ5ItHkz-3mVlsF_NnPS7NH1-EXwUW-s4VMxA,2617
 evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=mNHA_Fuj_gAdOEoR7oChnGmErf1czqwnk8Zk-jRhBys,1304
 evalscope/benchmarks/live_code_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -226,7 +235,7 @@ evalscope/benchmarks/math_vista/math_vista_adapter.py,sha256=Mu9BpH0rDNM0yMrGws4
 evalscope/benchmarks/minerva_math/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/minerva_math/minerva_math_adapter.py,sha256=jyT9_D4w8PTtLBN3Kn10_CnssH_mPuRNnn9rek_zUEs,1655
 evalscope/benchmarks/mm_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/mm_bench/mm_bench_adapter.py,sha256=py0DakGQX1JE2rqYjYN9w_-H0DtQ-YqG5k2s_UzbxxU,4372
+evalscope/benchmarks/mm_bench/mm_bench_adapter.py,sha256=ht2DVt_zEBJp4jvGy3myHHgdUUP9eff2O5BpIc9Fv74,4376
 evalscope/benchmarks/mm_star/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/mm_star/mm_star_adapter.py,sha256=oamLv6U2-JAK5mdVLkUgYxkOahxQkQYMRKAyu_xPAUE,2818
 evalscope/benchmarks/mmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -236,7 +245,7 @@ evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=GtIyUubUg6Q6Ydh1Adj0-32
 evalscope/benchmarks/mmlu_redux/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py,sha256=m_37OIFrJB4ZIvtbDJ_m9P9mA2QtrNjGfbbVo15awJg,7402
 evalscope/benchmarks/mmmu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/mmmu/mmmu_adapter.py,sha256=C7UM6HvomcA_Srf7771S0CaUvifBX63i161XaacraGQ,6038
+evalscope/benchmarks/mmmu/mmmu_adapter.py,sha256=WrykWq8n61CVrQ4XQhI3iEySgErHdZyng3udOL-Pddk,6054
 evalscope/benchmarks/mmmu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py,sha256=banPS1nDt9bQ95urKbSZnR-hBTw23eL9MSrHt_0ZLp0,4725
 evalscope/benchmarks/multi_if/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -248,6 +257,21 @@ evalscope/benchmarks/musr/musr_adapter.py,sha256=kx6bckj7Nijl4Wysuj-mKYdy0hIRDJh
 evalscope/benchmarks/needle_haystack/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py,sha256=GYaswWPwYI3aV5HSpcuBTgW9-HDtf2xzNZg0WrsI0Yo,17033
 evalscope/benchmarks/needle_haystack/utils.py,sha256=k8WDigqt5LgzHw6DtaYsLtb3BJL0FTZS9JOyJCpoPq8,2935
+evalscope/benchmarks/ocr_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/ocr_bench/ocr_bench_adapter.py,sha256=gkQb7g0-Lf5Sjemqs5kqogCLGFJI6YQv8-vGI1EbyLE,4392
+evalscope/benchmarks/ocr_bench_v2/IoUscore_metric.py,sha256=cBpRDJvI9f6vKRD4wTPv-8ThGddR3EhVobgjQQUAYlE,2606
+evalscope/benchmarks/ocr_bench_v2/TEDS_metric.py,sha256=31bL0V32Fq7prF1WoVjXmrmMdhg0qNcoiOaKykKOrZM,36528
+evalscope/benchmarks/ocr_bench_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/ocr_bench_v2/ocr_bench_v2_adapter.py,sha256=QGY4R75UxDafIwSaOEPPuCaX3Z8BGoZVvcc6OWbeO9w,7976
+evalscope/benchmarks/ocr_bench_v2/page_ocr_metric.py,sha256=d1nU7LNwubBd_1rIe7i67hOVcJx5IUXkqVeqt1CQzak,1624
+evalscope/benchmarks/ocr_bench_v2/parallel.py,sha256=Q54wFSSRBp-kG2MhW4eOoXE1W9g-SDVhN8JuphDERsE,2029
+evalscope/benchmarks/ocr_bench_v2/spotting_metric.py,sha256=nftLaTOKEmqvSWr-c20f9hyyvNnd-Hg3E46KwqmkjLc,6149
+evalscope/benchmarks/ocr_bench_v2/utils.py,sha256=z9DSh2m1yvM3vsvxvqdHuPgRFxgdmEnzuNIuO7PAV3s,15914
+evalscope/benchmarks/ocr_bench_v2/vqa_metric.py,sha256=XkAiXk1uE7lsWQQXvjnHXZMsga8B9FVyq5qG8ghePK4,8980
+evalscope/benchmarks/ocr_bench_v2/spotting_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/ocr_bench_v2/spotting_eval/readme.txt,sha256=QO0K9z1ethy_lgs9vaxGN1u5DnPFsssp8z62Cni24iw,1424
+evalscope/benchmarks/ocr_bench_v2/spotting_eval/rrc_evaluation_funcs_1_1.py,sha256=qCuqDtsCfxAiQHYLNdHU7BQ9kLIZ9iyfmRxtIrGOBck,20349
+evalscope/benchmarks/ocr_bench_v2/spotting_eval/script.py,sha256=7HzM1PEw8wNOhmQOsZe582Y2rr4u66Q3JKVvvMasntE,19565
 evalscope/benchmarks/olympiad_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/olympiad_bench/olympiad_bench_adapter.py,sha256=zePVmGjmyuwCWVb4h1PIQKAIFqBehwRwO2WOD0KX_ik,6565
 evalscope/benchmarks/olympiad_bench/utils.py,sha256=w7vEZcT3vCVq8_DSMgAjZPpVFVHStJPJYsPkrs-yOFM,21412
@@ -302,8 +326,8 @@ evalscope/filters/selection.py,sha256=yiJu2JjXDH_lgfEtB9umkGcA3zpo3zvnyoq2mKrXbn
 evalscope/metrics/__init__.py,sha256=1giVHESSjn98uBiAvYm5uLsmRQwmf9NHPSt7OT_QJss,1615
 evalscope/metrics/llm_judge.py,sha256=XukhH9PQtIZAcbjJlOmOD9ye3ngRv_IGKKJE9jhheOE,8653
 evalscope/metrics/math_parser.py,sha256=BMfautQtNNiF9f2DIEfO6SXSn_GYhzaddAjGWG10MJA,17257
-evalscope/metrics/metric.py,sha256=CabKKEbw_DptyH1ZQju7WzjB47fWUKdOhFB1ROpUC-4,10871
-evalscope/metrics/metrics.py,sha256=VxAggzEfaLKxWcXyuve8QbEBwV2W71udVyt0gynzGec,14134
+evalscope/metrics/metric.py,sha256=KNp_DNi9Ntq4my5G7La7AlP2Vj1p6hIgOheAh-4go5Q,12861
+evalscope/metrics/metrics.py,sha256=Y7TQ6MYaGE32EntTz-18CmQqYMpo1rQSvUiSwzBgpaQ,14599
 evalscope/metrics/rouge_metric.py,sha256=bqvSotuDdC0MEKmt8v6y6tBTBx0S3Ma-tfF-cMCckA4,4645
 evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
 evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=T91PgJfi1As7BR7I-Hq6rLlvHAtMB9JpBw9gMTH8VlE,12114
@@ -381,9 +405,9 @@ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py,sh
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/base_model.py,sha256=OOr1JD9kTlUGXZNG5b3kvkUaNz7QTmhaGoHhIKL69qo,7613
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py,sha256=Ns7oM4KpKxWZTo8Lefe4EDFw-jzp5633zAArcWjoVZA,9772
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py,sha256=KIF5tsiE7a5dbDfa-IKwzuzMUpuEAQPrm1nWFFtAeoI,20032
-evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py,sha256=uhaehowhTqRhQtq_dVCgF-9Iu4yU19AMxx2sJimYwlA,52711
+evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py,sha256=85ZvV2gKSnsbP5941PeJ-JJ4t8_lOYQe1EOxrHlIbNI,52728
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py,sha256=o5ykt3Q_WQlNmyxjQaS2-KPLGq1xqLZixNYam_Bs6NA,18701
-evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py,sha256=aBKdQQS7cHMPgYqIknCdHCZ7j2_QLACPn_jU_njiMIs,46840
+evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py,sha256=NPDpIRxjiroafZk5Z2uA9bC8Bi-yXY7um5HXxThF7N0,46857
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py,sha256=s7EkhtrIJ0LPUuLBArws8N23R1MoIoNaYUjwsbUqRkY,7994
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py,sha256=FnUyxxazEVaP69pAq9cig3j-mcX37BX-unPj0SVKUJI,3805
@@ -403,7 +427,7 @@ evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/bl
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py,sha256=TOAI-KaUrtKjR1GNU_WwNXNpb9gGT-KX2FYe3muv_e0,4275
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py,sha256=-DprR09KYuwNEzEbhPvFRI3MR4_VdPMUGLPN6sL9Ym8,14625
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py,sha256=S68U0DxWYGDmreRbH5yLDHBNN9PsczY9H0Uik0hO-ds,13872
-evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py,sha256=i1XlJe_PTSmiPkZKIhUXC_lc0-z2ewNYo4W1DvZQxjY,36678
+evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py,sha256=zv_WyHi67hvgHQ4DkZ8a4UoPcgrADKayqVtiIq-p3V4,36695
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py,sha256=p67DDiFS-676z0z8jPj6NwXwNjEsqTXaXCh3g2UiDno,840
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py,sha256=LqMHlUTy2LEzoVwjALtrAw0UYmzIuHnFjQiVmn5nv-I,605
 evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py,sha256=d4HInkL_Phk0Bgg2cWaOvhsPa6lkqDeovFW86PL0I18,6371
@@ -448,8 +472,8 @@ evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3S
 evalscope/perf/utils/local_server.py,sha256=_lSPlNEnOmPA_DtREgPS_vj2w_7D8PPSpypXbb0YfJM,4880
 evalscope/perf/utils/log_utils.py,sha256=NWSK_ITG4yoVx5GMLbIRGDoXSs90s7X3mftdm37Os2U,1666
 evalscope/perf/utils/rich_display.py,sha256=AQmXv1EuA1-IGgco-Jy1NLOmTKv4eBFH2K4QS8OoGVo,8206
-evalscope/report/__init__.py,sha256=DTigCg9fkU_zGNDqIaZy3CWYbrlvODvCxCTVqSx6ano,875
-evalscope/report/combinator.py,sha256=Xzlhs7kwfI6cgs7rngxhvsur0bCJkrM0tAy6isq2VME,3235
+evalscope/report/__init__.py,sha256=xS6eeTgsPdIlIOhzUn-ND77uV34vMVug4PmXHmYAxwM,1080
+evalscope/report/combinator.py,sha256=F7KOClXVh56-XEw3Sb5uxwA6L8ZlH_P4-MOlm3Yp_Cg,5020
 evalscope/report/generator.py,sha256=t2R3WGa4SowTRUPOgITtyTR4QDiJ6i3FH__byDKZU8Y,4959
 evalscope/report/report.py,sha256=lEBD_E_RJiydFTaGFNLIMTFxNrqv8QcLZb_iuUg5HB0,8479
 evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
@@ -494,41 +518,14 @@ evalscope/utils/deprecation_utils.py,sha256=aDv3HFNcJFZ7rxNgALQP0-ITO8L23HC_RX-C
 evalscope/utils/function_utils.py,sha256=E-AIzx_PKrZDGl1cBvlvqNvMa8yM2WUJ2wh73PNBXrQ,1887
 evalscope/utils/import_utils.py,sha256=S0WQ3gt4zpwJHjGcyC-604pWWExg3JV7f3wzoOH-tuo,5794
 evalscope/utils/io_utils.py,sha256=79F0p7dFxA84tIVSL_C4piJgeQQtVUfb2R_Xcd8v_cE,11615
-evalscope/utils/json_schema.py,sha256=ZExvQA-SI6SxWBx_hCmuQ2RRqwGKuywy4sTotvd2hH0,8288
+evalscope/utils/json_schema.py,sha256=GVP1m6g4mBrsFmOWOOVnmvl2joOz8gTlGEytLv5qy7s,8451
 evalscope/utils/logger.py,sha256=roFk4Su4aJwsF0s-uYc5-tABnghwYPX3gpkA5QUGzK8,5675
 evalscope/utils/model_utils.py,sha256=mdtYoHhUdfpxUtnS52XZjNdO3uSK4yeIBHT3aDU7s-A,2455
-evalscope/utils/multi_choices.py,sha256=OxBER7amWpoRY0Z-o39rDmCNK6wpr1HQm9mMHpWLgp0,9524
+evalscope/utils/multi_choices.py,sha256=0UJbgr5eXNgitPC79JLcyUU-OXg9BlM-mVk-fWtUSno,9881
 evalscope/utils/url_utils.py,sha256=9HcFt9uZNbOJR3ADUFQ_dBFKziHV6H66Df7HYs1M4Po,1757
-tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/common.py,sha256=BB136KcGaEfdWqMwApa48K0CTSGmOCUZ0FYDqpfYnAA,2423
-tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
-tests/utils.py,sha256=Fgm0CU6ilZjCGOfOMJH-Trxy0UIAGbhvy0Ijy_zDGUk,323
-tests/benchmark/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/benchmark/test_eval.py,sha256=vSAvhiCKxHpjHdGhZn8l0qzPSiG1ZZafz_M06B_a8_Y,13827
-tests/benchmark/test_image_edit.py,sha256=z3z7psMRFynpVgUAFoH--ieeGXzb9cHkrq3tT_sCZo8,2165
-tests/benchmark/test_sandbox.py,sha256=bHyX8ammdn7EsEbN80cIzDNhQZlJD3Ssoj9l4efF7rI,2968
-tests/benchmark/test_t2i.py,sha256=fciaGsOrkOpT4WQlsnmjrqw6qolCzI0DGyWQAJkM-Es,4513
-tests/benchmark/test_vlm.py,sha256=gn0ledf_yPY1IhCyCtiqT_dTVPUVZ3NVPr9yzsC_UZQ,4501
-tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/cli/test_all.py,sha256=1omOXC1lBphBLm0hTf5HNstlF_bwi16dYyr00gvaCTM,7301
-tests/cli/test_collection.py,sha256=lGz3YUS_0gM6_HjQLe26OfBAkHOPOEDWMO-UyP58GN8,4455
-tests/cli/test_custom.py,sha256=9z_N7Re712xI62TqVSTBdzB_iFFEUb55wcWIcGvJb84,9254
-tests/cli/test_reasoning.py,sha256=rU181LLoKbFCpNPFCIZULxEgsJ2PYswel2pP2EsjEmo,2696
-tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=ugYNEyU32ctryPFa_6fr8aQYxfHJMymdKnKKEHM9Ajc,6174
-tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/rag/test_clip_benchmark.py,sha256=qpSLgmHMGcYTnxP7AI__y-ii5_tu_fCSht6p3TBetkA,2650
-tests/rag/test_mteb.py,sha256=fdNQIyUEzE7puPCKw5QhCHTEu7hz-ieHeq1xCWGh6IM,7246
-tests/rag/test_ragas.py,sha256=5qozXvPFIb67T-igJv87ijlOgkPnqgkkBVXu6Ht4D0A,4554
-tests/swift/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/swift/test_run_swift_eval.py,sha256=YbIhYNoI4kAB-ox-OXAKUifLIXTFqP-xGZicrAgK_V0,5784
-tests/swift/test_run_swift_vlm_eval.py,sha256=RwrKkc1WHEZxetM11cGL81G4faKCn7SYn4VlwL03atI,4934
-tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=UAUtOCQ72xbm8s-sov3cBEpYVDy189wpB-qOL3KoU7M,6053
-tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/vlm/test_vlmeval.py,sha256=EDQRkYfSyOICUwo_tm3p-puaE_xdFmqOPkrt5etxsqM,3307
-evalscope-1.0.2.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-1.0.2.dist-info/METADATA,sha256=vZciS7qNosSJOdwyRSxsCyVqvw8hyqKS84yKjlbxwzw,40305
-evalscope-1.0.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-1.0.2.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-1.0.2.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-1.0.2.dist-info/RECORD,,
+evalscope-1.1.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-1.1.0.dist-info/METADATA,sha256=pap4NeCTqw7bec2KqYboFj25zabm1m5rwoiqukX8EO4,39544
+evalscope-1.1.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-1.1.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-1.1.0.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
+evalscope-1.1.0.dist-info/RECORD,,

{evalscope-1.0.2.dist-info → evalscope-1.1.0.dist-info}/top_level.txt

@@ -1,2 +1 @@
 evalscope
-tests