evalscope 0.15.1__py3-none-any.whl → 0.16.0__py3-none-any.whl

evalscope/report/app.py

@@ -223,6 +223,33 @@ def plot_multi_report_radar(df: pd.DataFrame):
     return fig
 
 
+def convert_markdown_image(text):
+    if not os.path.isfile(text):
+        return text
+    # Convert the image path to a markdown image tag
+    if text.endswith('.png') or text.endswith('.jpg') or text.endswith('.jpeg'):
+        text = os.path.abspath(text)
+        image_tag = f'![image](gradio_api/file={text})'
+        logger.debug(f'Converting image path to markdown: {text} -> {image_tag}')
+        return image_tag
+    return text
+
+
+def convert_html_tags(text):
+    # match begin label
+    text = re.sub(r'<(\w+)>', r'[\1]', text)
+    # match end label
+    text = re.sub(r'</(\w+)>', r'[/\1]', text)
+    return text
+
+
+def process_string(string: str, max_length: int = 2048) -> str:
+    string = convert_html_tags(string)  # for display labels e.g.
+    if max_length and len(string) > max_length:
+        return f'{string[:max_length // 2]}......{string[-max_length // 2:]}'
+    return string
+
+
 def dict_to_markdown(data) -> str:
     markdown_lines = []
 
@@ -230,55 +257,41 @@ def dict_to_markdown(data) -> str:
         bold_key = f'**{key}**'
 
         if isinstance(value, list):
-            value_str = '\n' + '\n'.join([f'  - {item}' for item in value])
+            value_str = '\n' + '\n'.join([f'- {process_model_prediction(item, max_length=None)}' for item in value])
         elif isinstance(value, dict):
             value_str = dict_to_markdown(value)
         else:
             value_str = str(value)
 
-        value_str = process_string(value_str)
-        markdown_line = f'{bold_key}: {value_str}'
+        value_str = process_string(value_str, max_length=None)  # Convert HTML tags but don't truncate
+        markdown_line = f'{bold_key}:\n{value_str}'
         markdown_lines.append(markdown_line)
 
     return '\n\n'.join(markdown_lines)
 
 
-def convert_html_tags(text):
-    # match begin label
-    text = re.sub(r'<(\w+)>', r'[\1]', text)
-    # match end label
-    text = re.sub(r'</(\w+)>', r'[/\1]', text)
-    return text
-
-
-def convert_markdown_image(text):
-    if not os.path.isfile(text):
-        return text
-    # Convert the image path to a markdown image tag
-    if text.endswith('.png') or text.endswith('.jpg') or text.endswith('.jpeg'):
-        text = os.path.abspath(text)
-        image_tag = f'![image](gradio_api/file={text})'
-        logger.debug(f'Converting image path to markdown: {text} -> {image_tag}')
-        return image_tag
-    return text
+def process_model_prediction(item: Any, max_length: int = 2048) -> str:
+    """
+    Process model prediction output into a formatted string.
 
+    Args:
+        item: The item to process. Can be a string, list, or dictionary.
+        max_length: The maximum length of the output string.
 
-def process_string(string: str, max_length: int = 2048) -> str:
-    string = convert_html_tags(string)  # for display labels e.g. `<think>`
-    if len(string) > max_length:
-        return f'{string[:max_length // 2]}......{string[-max_length // 2:]}'
-    return string
-
-
-def process_model_prediction(item: Any):
+    Returns:
+        A formatted string representation of the input.
+    """
     if isinstance(item, dict):
-        res = dict_to_markdown(item)
-        return process_string(res)
+        result = dict_to_markdown(item)
     elif isinstance(item, list):
-        res = '\n'.join([process_model_prediction(item) for item in item])
-        return process_string(res)
+        result = '\n'.join([f'- {process_model_prediction(i, max_length=None)}' for i in item])
     else:
-        return process_string(str(item))
+        result = str(item)
+
+    # Apply HTML tag conversion and truncation only at the final output
+    if max_length is not None:
+        return process_string(result, max_length)
+    return result
 
 
 def normalize_score(score):

evalscope/report/utils.py

@@ -96,7 +96,7 @@ class Report:
 
     @classmethod
     def from_json(cls, json_file: str):
-        with open(json_file, 'r') as f:
+        with open(json_file, 'r', encoding='utf-8') as f:
             data = json.load(f)
         return cls.from_dict(data)
 

evalscope/third_party/toolbench_static/toolbench_static.py

@@ -6,11 +6,12 @@ from typing import Union
 from evalscope.third_party.toolbench_static.eval import EvalArgs, run_eval
 from evalscope.third_party.toolbench_static.infer import InferArgs, run_infer
 from evalscope.utils import get_logger
+from evalscope.utils.deprecation_utils import deprecated
 from evalscope.utils.io_utils import json_to_dict, yaml_to_dict
 
 logger = get_logger()
 
-
+@deprecated(since='0.15.1', remove_in='0.18.0', alternative='Native implementation of ToolBench')
 def run_task(task_cfg: Union[str, dict]):
 
     if isinstance(task_cfg, str):

evalscope/utils/deprecation_utils.py

@@ -0,0 +1,42 @@
+import functools
+import inspect
+from typing import Callable, Optional
+
+from .logger import get_logger
+
+logger = get_logger()
+
+
+def deprecated(since: str, remove_in: Optional[str] = None, alternative: Optional[str] = None) -> Callable:
+    """
+    Decorator to mark functions as deprecated.
+
+    :param since: String indicating the version since deprecation
+    :param remove_in: Optional string indicating the version when it will be removed
+    :param alternative: Optional string suggesting an alternative
+    :return: Decorated function
+    """
+
+    def decorator(func: Callable) -> Callable:
+
+        @functools.wraps(func)
+        def wrapper(*args, **kwargs):
+            # Get the file name where the function is defined
+            file_name = inspect.getfile(func)
+
+            # Construct the warning message
+            warning_parts = [
+                f'{func.__name__} in {file_name} has been deprecated since version {since}',
+                f'and will be removed in version {remove_in}' if remove_in else None,
+                f'Use {alternative} instead' if alternative else None
+            ]
+            warning_message = '. '.join(filter(None, warning_parts))
+
+            # Log the warning
+            logger.warning(warning_message)
+
+            return func(*args, **kwargs)
+
+        return wrapper
+
+    return decorator

evalscope/version.py

@@ -1,4 +1,4 @@
 # Copyright (c) Alibaba, Inc. and its affiliates.
 
-__version__ = '0.15.1'
-__release_datetime__ = '2025-04-30 12:00:00'
+__version__ = '0.16.0'
+__release_datetime__ = '2025-05-19 18:00:00'

{evalscope-0.15.1.dist-info → evalscope-0.16.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: evalscope
-Version: 0.15.1
+Version: 0.16.0
 Summary: EvalScope: Lightweight LLMs Evaluation Framework
 Home-page: https://github.com/modelscope/evalscope
 Author: ModelScope team
@@ -91,9 +91,10 @@ Requires-Dist: webdataset>0.2.0; extra == "all"
 Requires-Dist: aiohttp; extra == "all"
 Requires-Dist: fastapi; 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: unicorn; extra == "all"
+Requires-Dist: uvicorn; extra == "all"
 Requires-Dist: gradio==5.4.0; extra == "all"
 Requires-Dist: plotly<6.0.0,>=5.23.0; extra == "all"
 Requires-Dist: diffusers; extra == "all"
@@ -110,9 +111,10 @@ Provides-Extra: perf
 Requires-Dist: aiohttp; extra == "perf"
 Requires-Dist: fastapi; extra == "perf"
 Requires-Dist: numpy; extra == "perf"
+Requires-Dist: rich; extra == "perf"
 Requires-Dist: sse-starlette; extra == "perf"
 Requires-Dist: transformers; extra == "perf"
-Requires-Dist: unicorn; extra == "perf"
+Requires-Dist: uvicorn; extra == "perf"
 Provides-Extra: rag
 Requires-Dist: langchain<0.4.0,>=0.3.0; extra == "rag"
 Requires-Dist: langchain-community<0.4.0,>=0.3.0; extra == "rag"
@@ -177,9 +179,23 @@ Requires-Dist: ms-vlmeval>=0.0.9; extra == "vlmeval"
 
 ## 📝 Introduction
 
-EvalScope is [ModelScope](https://modelscope.cn/)'s official framework for model evaluation and benchmarking, designed for diverse assessment needs. It supports various model types including large language models, multimodal, embedding, reranker, and CLIP models.
+EvalScope is a comprehensive model evaluation and performance benchmarking framework meticulously crafted by the [ModelScope Community](https://modelscope.cn/), offering a one-stop solution for your model assessment needs. Regardless of the type of model you are developing, EvalScope is equipped to cater to your requirements:
 
-The framework accommodates multiple evaluation scenarios such as end-to-end RAG evaluation, arena mode, and inference performance testing. It features built-in benchmarks and metrics like MMLU, CMMLU, C-Eval, and GSM8K. Seamlessly integrated with the [ms-swift](https://github.com/modelscope/ms-swift) training framework, EvalScope enables one-click evaluations, offering comprehensive support for model training and assessment 🚀
+- 🧠 Large Language Models
+- 🎨 Multimodal Models
+- 🔍 Embedding Models
+- 🏆 Reranker Models
+- 🖼️ CLIP Models
+- 🎭 AIGC Models (Image-to-Text/Video)
+- ...and more!
+
+EvalScope is not merely an evaluation tool; it is a valuable ally in your model optimization journey:
+
+- 🏅 Equipped with multiple industry-recognized benchmarks and evaluation metrics: MMLU, CMMLU, C-Eval, GSM8K, etc.
+- 📊 Model inference performance stress testing: Ensuring your model excels in real-world applications.
+- 🚀 Seamless integration with the [ms-swift](https://github.com/modelscope/ms-swift) training framework, enabling one-click evaluations and providing full-chain support from training to assessment for your model development.
+
+Below is the overall architecture diagram of EvalScope:
 
 <p align="center">
   <img src="docs/en/_static/images/evalscope_framework.png" width="70%">
@@ -214,6 +230,8 @@ Please scan the QR code below to join our community groups:
 
 ## 🎉 News
 
+- 🔥 **[2025.05.16]** Model service performance stress testing now supports setting various levels of concurrency and outputs a performance test report. [Reference example](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/quick_start.html#id3).
+- 🔥 **[2025.05.13]** Added support for the [ToolBench-Static](https://modelscope.cn/datasets/AI-ModelScope/ToolBench-Static) dataset to evaluate model's tool-calling capabilities. Refer to the [documentation](https://evalscope.readthedocs.io/en/latest/third_party/toolbench.html) for usage instructions. Also added support for the [DROP](https://modelscope.cn/datasets/AI-ModelScope/DROP/dataPeview) and [Winogrande](https://modelscope.cn/datasets/AI-ModelScope/winogrande_val) benchmarks to assess the reasoning capabilities of models.
 - 🔥 **[2025.04.29]** Added Qwen3 Evaluation Best Practices, [welcome to read 📖](https://evalscope.readthedocs.io/en/latest/best_practice/qwen3.html)
 - 🔥 **[2025.04.27]** Support for text-to-image evaluation: Supports 8 metrics including MPS, HPSv2.1Score, etc., and evaluation benchmarks such as EvalMuse, GenAI-Bench. Refer to the [user documentation](https://evalscope.readthedocs.io/en/latest/user_guides/aigc/t2i.html) for more details.
 - 🔥 **[2025.04.10]** Model service stress testing tool now supports the `/v1/completions` endpoint (the default endpoint for vLLM benchmarking)
@@ -479,26 +497,27 @@ For more customized evaluations, such as customizing model parameters or dataset
 
 ```shell
 evalscope eval \
- --model Qwen/Qwen2.5-0.5B-Instruct \
- --model-args revision=master,precision=torch.float16,device_map=auto \
- --generation-config do_sample=true,temperature=0.5 \
+ --model Qwen/Qwen3-0.6B \
+ --model-args '{"revision": "master", "precision": "torch.float16", "device_map": "auto"}' \
+ --generation-config '{"do_sample":true,"temperature":0.6,"max_new_tokens":512,"chat_template_kwargs":{"enable_thinking": false}}' \
  --dataset-args '{"gsm8k": {"few_shot_num": 0, "few_shot_random": false}}' \
  --datasets gsm8k \
  --limit 10
 ```
 
-### Parameter
-- `--model-args`: Model loading parameters, separated by commas in `key=value` format. Default parameters:
-  - `revision`: Model version, default is `master`
-  - `precision`: Model precision, default is `auto`
-  - `device_map`: Model device allocation, default is `auto`
-- `--generation-config`: Generation parameters, separated by commas in `key=value` format. Default parameters:
-  - `do_sample`: Whether to use sampling, default is `false`
-  - `max_length`: Maximum length, default is 2048
-  - `max_new_tokens`: Maximum length of generation, default is 512
-- `--dataset-args`: Configuration parameters for evaluation datasets, passed in `json` format. The key is the dataset name, and the value is the parameters. Note that it needs to correspond one-to-one with the values in the `--datasets` parameter:
+### Parameter Description
+- `--model-args`: Model loading parameters, passed as a JSON string:
+  - `revision`: Model version
+  - `precision`: Model precision
+  - `device_map`: Device allocation for the model
+- `--generation-config`: Generation parameters, passed as a JSON string and parsed as a dictionary:
+  - `do_sample`: Whether to use sampling
+  - `temperature`: Generation temperature
+  - `max_new_tokens`: Maximum length of generated tokens
+  - `chat_template_kwargs`: Model inference template parameters
+- `--dataset-args`: Settings for the evaluation dataset, passed as a JSON string where the key is the dataset name and the value is the parameters. Note that these need to correspond one-to-one with the values in the `--datasets` parameter:
   - `few_shot_num`: Number of few-shot examples
-  - `few_shot_random`: Whether to randomly sample few-shot data, if not set, defaults to `true`
+  - `few_shot_random`: Whether to randomly sample few-shot data; if not set, defaults to `true`
 
 Reference: [Full Parameter Description](https://evalscope.readthedocs.io/en/latest/get_started/parameters.html)
 
@@ -517,6 +536,11 @@ A stress testing tool focused on large language models, which can be customized
 
 Reference: Performance Testing [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test/index.html)
 
+**Output example**
+
+![multi_perf](docs/en/user_guides/stress_test/images/multi_perf.png)
+
+
 **Supports wandb for recording results**
 
 ![wandb sample](https://modelscope.oss-cn-beijing.aliyuncs.com/resource/wandb_sample.png)
@@ -565,7 +589,7 @@ EvalScope, as the official evaluation tool of [ModelScope](https://modelscope.cn
 </a>
 
 ## 🔜 Roadmap
-- [ ] Support for better evaluation report visualization
+- [x] Support for better evaluation report visualization
 - [x] Support for mixed evaluations across multiple datasets
 - [x] RAG evaluation
 - [x] VLM evaluation
@@ -575,7 +599,7 @@ EvalScope, as the official evaluation tool of [ModelScope](https://modelscope.cn
 - [x] Multi-modal evaluation
 - [ ] Benchmarks
   - [ ] GAIA
-  - [ ] GPQA
+  - [x] GPQA
   - [x] MBPP
 
 

{evalscope-0.15.1.dist-info → evalscope-0.16.0.dist-info}/RECORD

@@ -1,11 +1,11 @@
 evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=jywTxu_HWhgf0_OlnaOyRSzUHenr5Zio2vmcCgcfbxg,5453
-evalscope/config.py,sha256=O3kjjVFRGSrlLD5EI4t99Z-m6oFtQVmEudvE62x92wY,9648
+evalscope/arguments.py,sha256=fZW-om5E2_JaFcEmkvahvundjedPLgIDde-zwDXinG0,5868
+evalscope/config.py,sha256=19QaZ5VS8wknt4sLBxiZkR6pH-nm4Ph3Kl-1bZgcQcE,10799
 evalscope/constants.py,sha256=PHnsGndB4N5-jvmawPxMK5b9geE2Es5cUe8ZKYSuKgM,4016
 evalscope/run.py,sha256=_DKbxgQGwhweBnQrI7lQhu5eoz4LYPVeNanzD4lHuJA,6476
 evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
 evalscope/summarizer.py,sha256=61kU5ZoSh1dd8HMJPqP3ZvJwcY9szwWFCZdu2lfATJA,5920
-evalscope/version.py,sha256=eFCP5Hfk4dip59uCASefVxaNqxWNtwDQPrqaoRJxO9c,119
+evalscope/version.py,sha256=8STVV6Y877B3esrgvovInSk4IFNzxZ_ZEz9ND_6B2lQ,119
 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
@@ -50,14 +50,14 @@ evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py,sha256=6x-4O2pgsjZCVf
 evalscope/backend/rag_eval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/backend/rag_eval/utils/clip.py,sha256=GLHhPCac2AH35AvRLvVqePA1gIMAewHTFmCJCDZzvqU,5015
 evalscope/backend/rag_eval/utils/embedding.py,sha256=tFMepPAMO4Kkqeqh-XxXIDYRjGbCMlk7lwuUW7FNvCA,7977
-evalscope/backend/rag_eval/utils/llm.py,sha256=acaD5QHPJUstJGpW1sNJ-3ZPT5J_Z8beOWb61Rtz07U,2607
+evalscope/backend/rag_eval/utils/llm.py,sha256=NHjm0SeQVsSIG8uISXZcQypku4QRc3KtteeO9ldv0FI,2611
 evalscope/backend/rag_eval/utils/tools.py,sha256=FU7tNu-8y8V_o_kArFVTTLM_GzL12KBNeXiwQw5SpJA,1529
 evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4tycyy-FJgzLdjeY,84
 evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=sUYvQxCtPl6CrcwhQpY8lJjW5skqWc-fvHUSnXd_MvQ,6054
 evalscope/benchmarks/__init__.py,sha256=5AXNhhmbaBFEe3u7y5TtIrviYzFI-hC8oKqxFILs1pE,937
 evalscope/benchmarks/benchmark.py,sha256=a_7Ctz36McuTyBSTYi56jis9pvOdWhg7JVSPFrbxqR4,2535
-evalscope/benchmarks/data_adapter.py,sha256=mWdxtHbordS577NqZUQZmIjlewjGDlStqc-iDvqpAyU,18061
-evalscope/benchmarks/utils.py,sha256=yXQyszzrILNiBuUrbB1BtgotQSaNA8w6X935AL1dNAw,1074
+evalscope/benchmarks/data_adapter.py,sha256=lcBoXhI1Byn0HcwbVxmIeUFxZlz_wiqte6RDPOR8sbM,18184
+evalscope/benchmarks/utils.py,sha256=jB9w3mN1eOur6j2kpQB_XZJ912fhzC0GaSeHOoylK7M,1087
 evalscope/benchmarks/aigc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aigc/t2i/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/aigc/t2i/base.py,sha256=4GFAvceT1Gpt5teDLRCZi62RwvPazuhG3zwft3gN3X4,2102
@@ -70,7 +70,7 @@ evalscope/benchmarks/aime/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJW
 evalscope/benchmarks/aime/aime24_adapter.py,sha256=GrIxCHpUwgUy8tXGTB7iQOt8k7wG8MJB0CWbwBmIy-8,1703
 evalscope/benchmarks/aime/aime25_adapter.py,sha256=yxo5roCb8ryX9ROUU2FdZ-WBTUPZ14MrBzEL0zPOh-U,1718
 evalscope/benchmarks/alpaca_eval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=em1YM2PxnJ8Of7Li3eqrw8PtwfeXSinfVIr-CIKVb60,4026
+evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py,sha256=oUHpWrt5Gx0jF80RBd7zTh_1AWI66YvDd6U1vOMoqj0,3828
 evalscope/benchmarks/arc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/arc/ai2_arc.py,sha256=WtL4Z_ulcCU2KfptWTjTm75T2I2rVGd9aDBBB76P14w,5697
 evalscope/benchmarks/arc/arc_adapter.py,sha256=0h-eT4BBmUJQrakKMPUNE1nSRwK6LHB-cflWpWzY978,6364
@@ -110,7 +110,7 @@ evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTP
 evalscope/benchmarks/ceval/ceval_adapter.py,sha256=1ITBXI0f01Dt1p7sb2RGswIeg9685Bkk2S2xmA1vat8,11295
 evalscope/benchmarks/ceval/ceval_exam.py,sha256=ngOvb6Fymt7iPWIb2fzrUVpqmUT2VBoqh7X_IH8Bcsc,4824
 evalscope/benchmarks/chinese_simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=zY8dfvrTeCHAQ3d7AM02CexZw5CVKH51ZOhtT7Q1Gko,8031
+evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py,sha256=Q6ncuLrCUrrhhljIfMsgWnyhHfcWWwh8iA6NZvz3W28,8079
 evalscope/benchmarks/cmmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/cmmlu/cmmlu.py,sha256=Y59NIGUFzJEztJbkehZsG4Cz0J_v9Cyju6xazHMYIcA,5022
 evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=r9zael_Y2Jso0ashevYpF8e5SHOBh8iMcPIJU5WT3pQ,10367
@@ -120,10 +120,13 @@ evalscope/benchmarks/competition_math/competition_math.py,sha256=Cehyokift7oDKjc
 evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=wgejW-_QswtT8_3JKAQ_H6svH8IotDJDBEH7X4nP4bY,6760
 evalscope/benchmarks/data_collection/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/data_collection/data_collection_adapter.py,sha256=QgLgIrjD3q53T-lu1UWTV6T4h1cKGoCQDh0O4QxFezw,2569
+evalscope/benchmarks/drop/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/drop/drop_adapter.py,sha256=V-Vx6g2_1kcDUDWOKVX1vPSLt5iHn8NQkpWbsIwPaa4,8325
+evalscope/benchmarks/drop/utils.py,sha256=Z9PHrNnRfGqFHCLONg5SWKARp1eTJlHFc_bU46t_YrM,1344
 evalscope/benchmarks/general_mcq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/general_mcq/general_mcq_adapter.py,sha256=fqbt61owPP7t2H4B2zbYVZTs0VBGuXNvWGvkukwhRYc,5039
 evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=I2BanmO4WLrKviyLiIeqmS5mdyjqGg1X7hauv4HBjgk,4653
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=40mZovspVf-OXcuEu3ei6G_HZlYA8whAHSESHPPONxA,4750
 evalscope/benchmarks/gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/gpqa/chain_of_thought.txt,sha256=pgoT5a-DMPJaMhoH_M8zfU5s80ibWDTVW6vnonITd8k,5610
 evalscope/benchmarks/gpqa/gpqa_adapter.py,sha256=UB287DtnbkSQXZsbReFJqmQRwbo672DTCeXXilR_-Vc,4790
@@ -174,12 +177,15 @@ evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO
 evalscope/benchmarks/race/race_adapter.py,sha256=RD0B-i5dzeNKuhqnWbremgf4tk9jmOO4_eLAiITB1F0,6381
 evalscope/benchmarks/race/samples.jsonl,sha256=bhSktBgU6axYQCClRtQ7nN8D1x815AU8xMAIG1oflG0,1243
 evalscope/benchmarks/simple_qa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=to4kSKc29BmtG4q9R2PeM-sdHiL8toSyoVi1D9WMRKk,8949
+evalscope/benchmarks/simple_qa/simple_qa_adapter.py,sha256=TD7hkMLGZ4GK7wD7cwqJ3jCcTAaixOakUy3o5DaPYHI,8997
 evalscope/benchmarks/super_gpqa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/benchmarks/super_gpqa/five_shot_prompt.txt,sha256=vD3RMeQustxY_oWA8IobntjywT8ZUO7Jaub--rElDT4,4718
 evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py,sha256=BqNLL8BYnK6tRuIdV6ijL4Uym2SejH_h1BV06XNjSE4,9331
 evalscope/benchmarks/super_gpqa/utils.py,sha256=ftYPP9ODvLBlQSd9ltACx9iRIvjB8u1bg4AtgcJ4JAI,3360
 evalscope/benchmarks/super_gpqa/zero_shot_prompt.txt,sha256=y7hR9SmoR_YqoEWtT8N9JpZOpeJIlg0cDGDgYw6R6hM,237
+evalscope/benchmarks/tool_bench/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/tool_bench/tool_bench_adapter.py,sha256=l2dBcJ4Z3m-8QFtfyFH4IqMtvkY3Rfk021P9Ff_lXWQ,2270
+evalscope/benchmarks/tool_bench/utils.py,sha256=vIPsL8FmMF2JZRHCZeLS_dDeATKNRvZDbq6T-Znlk8Q,7025
 evalscope/benchmarks/trivia_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/trivia_qa/samples.jsonl,sha256=1isBD62PGhCiNbzQa-GFrHHL4XLHIkojWfgSvn7ktf8,3445
 evalscope/benchmarks/trivia_qa/trivia_qa.py,sha256=eekxaXppMLb5tCQqNLOw2MaWlYDhI2IicPzRsTHqb5A,3070
@@ -187,6 +193,8 @@ evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=7tMc8vVZdBnks5jWrBSrb
 evalscope/benchmarks/truthful_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/benchmarks/truthful_qa/truthful_qa.py,sha256=A4abSL6WMRcXez8flxsHy-0ZFyRg-moq9rTeOA1TalY,6909
 evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=ueUU860kg5_xf_MtUCa6ck-fGHX3ttw8Xh3mWSJyOZA,12617
+evalscope/benchmarks/winogrande/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+evalscope/benchmarks/winogrande/winogrande_adapter.py,sha256=UdANz3YmCtV2YfGuEihTe3vpUTlIxeXBhIqGkKbTFdU,1956
 evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
 evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
@@ -195,22 +203,22 @@ evalscope/cli/start_eval.py,sha256=MXhVDeaMFd6ny88-gnVtQflH660UaDj240YGYnHccx8,7
 evalscope/cli/start_perf.py,sha256=5hLi5jWgM9BJPXLd8d9D1zqrcj_5c0KvkfB1DgD4_RU,831
 evalscope/cli/start_server.py,sha256=DQRIfbsHaOAsVcLGF6iRyJnxmd5Sf_tgytpJNfiWCeE,3662
 evalscope/collections/__init__.py,sha256=hd68Qf-ryeDsz5Pu-Dh83M5V5RE5mhLsG-vc55n5n0o,228
-evalscope/collections/evaluator.py,sha256=Ll-qLet04aEp1WxoCKAuvZVWEZuy1lS_D-vZIN3zSQQ,13425
+evalscope/collections/evaluator.py,sha256=3sz_bL0HMFkxq3C-4P6rNGrnQolifVISI5sEpT3Bt90,15754
 evalscope/collections/sampler.py,sha256=2NwvhJVdi-mrDeK7RWwEGOoE7DdxtpyASRUZU_D6hWw,4855
 evalscope/collections/schema.py,sha256=mjJfNmy_athJ1TmnuJRkrKRlefzefuQXZuTtjn8SHKo,4073
 evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
-evalscope/evaluator/evaluator.py,sha256=oOVYRMMQfT3fqu-l33wmJtKlyeWxwoIUADMCoBNARTM,20271
+evalscope/evaluator/evaluator.py,sha256=QzTFXiv_WdPpWTB3PgBNIz9KS_Rxu-fWDvoUpML23aA,21651
 evalscope/evaluator/rating_eval.py,sha256=uo0uj9z_TDsxdYlT8WIfNZhFLAfRkW9zn_wlu-F72O0,5575
 evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/evaluator/reviewer/auto_reviewer.py,sha256=5WRYuXFTDgVmolrOdiTysk-mXrpw6Qg87-iuY-VD1W4,16618
 evalscope/metrics/__init__.py,sha256=y1sdj5FBKYW1q5kLC6QREzoITHwstJRUdji6p0X5aAE,1363
-evalscope/metrics/llm_judge.py,sha256=MjyTC-xiSThk8Rd4IdUbsCXeeikoOORv6wt8H7SW8s4,4008
+evalscope/metrics/llm_judge.py,sha256=qYHsoBz-zXjL57Czl9CaPcyJT5SZr05giv5Q9SFK3cY,4000
 evalscope/metrics/math_parser.py,sha256=uTDudn305G3b8-GboWTrDE6OfrEwAW-areHnoGXZ6Is,17302
 evalscope/metrics/metrics.py,sha256=_YI7RhxlFu_JOgeE3LF9UKu6mJruvyu4FgqVf78Bjb8,13813
 evalscope/metrics/named_metrics.py,sha256=PrzU_1mGTeRFxVJFT1aXxIOiS7MnNoWyZsb8uCRVDeE,2278
-evalscope/metrics/rouge_metric.py,sha256=zhIUqenSuxnORR9tamLQBGjFwP91Zei2UiLtcOyseVM,4639
+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=Kq6AObenmLVQ5tN3NgN042a6mgRFQmRO21-ohd9mSa8,11972
+evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=m7v8ZysO9zCuyThEoGTe5QNVt2GsKMgZpH6du1FQCvg,12110
 evalscope/metrics/t2v_metrics/__init__.py,sha256=GBxgKTPVy_qhW_F3M4Oi6QMWhdAi4PqGX5w3t6Tueho,1783
 evalscope/metrics/t2v_metrics/clipscore.py,sha256=IsrYKIlFb04-FfBq4MbSv4diS6706J15Y3G4qEFIwfU,455
 evalscope/metrics/t2v_metrics/constants.py,sha256=oY5l5fOFl8qylah9eeebZm0pgY1PYmHDa7JlUC8Qls0,451
@@ -318,19 +326,19 @@ evalscope/models/model.py,sha256=MxvJAUNkuT7IA3bchnmJDur_YCKj9ShOD2Uq40dBcGc,630
 evalscope/models/register.py,sha256=pNC69YUvw-lodYpOXmByHm26h4m0Lofgd_om-JhOBq4,1882
 evalscope/models/adapters/__init__.py,sha256=mduiDZ6LgmkefNf4CtObZk6heOB93HxxgqTuYvrqWoo,590
 evalscope/models/adapters/base_adapter.py,sha256=f2FY8DLERudkfb4_anxNVFE_D19xCJj9BObiHWspewI,3268
-evalscope/models/adapters/chat_adapter.py,sha256=hzFrpvIrakKO5hsnbdXiDTO0cGajAdhcAN9ENoI6XvY,7312
+evalscope/models/adapters/chat_adapter.py,sha256=PAClyBL_nQ1I1kmjeeZ3sdC-y5ZmfFj8rjCigh_vr40,7885
 evalscope/models/adapters/choice_adapter.py,sha256=4fuz3MFEqK8ln4mMs3goMCdRPBwYmmgN70HTdr_sW_U,8005
 evalscope/models/adapters/custom_adapter.py,sha256=w8cD0b3xgcdhSZelcat67CGJnALOfz5IALzURnLjab8,2275
-evalscope/models/adapters/server_adapter.py,sha256=5kH1yDAjETogR7aOdnCEueYE1bREI40OdXdBiJpMdIM,6734
+evalscope/models/adapters/server_adapter.py,sha256=d-0ne7ymWXmvKf_ypJ0093RNwplZJwhvU2xRwc8rt70,6581
 evalscope/models/adapters/t2i_adapter.py,sha256=xkMRyZ61yTiJfmULK-p9du4nNox41pkHiV2CTFBO3qM,2659
 evalscope/models/custom/__init__.py,sha256=MZylegALg1HerOYtp-qbzu4Wb6PW3JbrxwONHU-PAVs,131
 evalscope/models/custom/custom_model.py,sha256=rBQLAuPEw_OPUtRSCEmxEfpcA8jPj8bAdsmtKs4ygus,1566
 evalscope/models/custom/dummy_model.py,sha256=WRT_aCBZLXnC4yRCgggkuySkhM71C47O2Txx_YNc3UM,1933
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/arguments.py,sha256=UZKlkbDE2N408dY8Ji-WB8sl1rcmamywzxLvNXpnY0w,10194
-evalscope/perf/benchmark.py,sha256=C0tLaZzxqMonZK4iLtfjiQIxX3tO3-uFrOjgV-oVsU0,8024
+evalscope/perf/arguments.py,sha256=5dTtaBR9BIobaKkX1Xj-mphHDG4uugnGaVOvWpLfN04,10714
+evalscope/perf/benchmark.py,sha256=eGnxMLQXSYBGRJS4tS8geSJAirnuWo35M4orlRZzei8,7847
 evalscope/perf/http_client.py,sha256=-c3-N7bxKsj3d5DVsKSaYA3XAHJDzZgoqZBbhuDYIGk,7419
-evalscope/perf/main.py,sha256=C7iNEdb4SEMGmHsF4DHAak4O1zRxrWW1tMRmyhEkVwQ,1376
+evalscope/perf/main.py,sha256=clHzkQNmv7wv-OWkuNGDQ-8YoLUCWxARIX-Eisinpms,3096
 evalscope/perf/plugin/__init__.py,sha256=1sl5s-csrwKb_LVTnpF3HqArz06TRD5LYJ0hpqvokUA,85
 evalscope/perf/plugin/registry.py,sha256=w1IAt6GDdluzSYK5i-yrntvx3_EvIIqJamEL0xZv3zA,1323
 evalscope/perf/plugin/api/__init__.py,sha256=Ckzbq4CkSMVQTedQcDHCYlRd6FTwQAElt2mHB-VXJac,195
@@ -349,11 +357,12 @@ evalscope/perf/plugin/datasets/random_dataset.py,sha256=SIlsjAE_Stknfr6o1CBFvANB
 evalscope/perf/plugin/datasets/speed_benchmark.py,sha256=J6q7AF_Re5eHLVejXEw9c1jlk1T1PPmist0yO9UFTPE,2432
 evalscope/perf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 evalscope/perf/utils/analysis_result.py,sha256=ESzaZHGTpr2LoJR3jpOzqMphxSrr79d364ZzD159PmY,1169
-evalscope/perf/utils/benchmark_util.py,sha256=CftjnxYA7d1aeAL_iuyXcJPwCL5A8zWGZSkNtjrMyW8,6309
-evalscope/perf/utils/db_util.py,sha256=VsYgz6IsSNPAWGCopOOIxAUhUat3GRbZMlrfdZ6i4kM,9575
+evalscope/perf/utils/benchmark_util.py,sha256=PcRTeKlEIslBw0zKVS2mFg6GgJ6J8m1f2-gAaEBeiHI,7236
+evalscope/perf/utils/db_util.py,sha256=xqrXZapP_WwUdzkgFBTh3LDBWzr_UoU8v13rOjQ8TT4,9876
 evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
 evalscope/perf/utils/local_server.py,sha256=clF8i0UFmaxBBB6gX05KvVCyzSv0xzsAidz0_sLLlAk,4627
-evalscope/perf/utils/log_utils.py,sha256=1jmB31W3ol9ukPAPbQ8xG3yoZ9oi3tjEyMK5M3ERmbw,1471
+evalscope/perf/utils/log_utils.py,sha256=Xm5A8g8BaozaI_0TaPzr2aAxUBCCf-w7II-FcifrIYg,1503
+evalscope/perf/utils/rich_display.py,sha256=SavP2L44UwN58ZUGR2W1wxM4h4F1iyPa90HhT-Ypkzs,8125
 evalscope/registry/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/registry/config/cfg_arena.yaml,sha256=rub6ceaQxxB1mbSjdoFf0IaVgGfbOonV2nYRebv2OKo,3292
 evalscope/registry/config/cfg_arena_zhihu.yaml,sha256=tvvihBwvoTjoezwTSaZwoGOB44ysofpnin4pNyY9TfQ,2755
@@ -376,11 +385,11 @@ evalscope/registry/tasks/gsm8k.yaml,sha256=M2I7otwOSy0usD8yG8d6QziASQlKdhKLflRHM
 evalscope/registry/tasks/mmlu.yaml,sha256=cJcMH1Cvgo9PlYoTmeGx2bcZayysltaa6ehK57dDkvo,726
 evalscope/registry/tasks/mmlu_mini.yaml,sha256=K8ouHh7ve5ZsbkqRtV3Jl-DF01YFPuObfwEdACJA4Pk,778
 evalscope/report/__init__.py,sha256=iLNqx7CnHSHQmOBqWUK_vt2VIjnvGslJTqn--7B4y_s,316
-evalscope/report/app.py,sha256=8pcQi5oYAYa9hXoMoMUNfy9jSvSR9DDiXyLcyPd9AmA,28459
+evalscope/report/app.py,sha256=FxNpiEmbpH_B7D5SYN42idGsyOgkgFrLzScOVrwL3SI,28998
 evalscope/report/app_arguments.py,sha256=1wHTLeFx1G94cKXYOeOVe_wTiOY2D929UctIRGOtRaQ,699
 evalscope/report/combinator.py,sha256=O3QirwtYhDhdaWVT4STJMCGZMwoX8BTeJ3HtS9iwnWQ,2567
 evalscope/report/generator.py,sha256=q9aHWNjQgvutAKtpjfWOpfu5zNFdnXilO9OqBqt_Phg,3612
-evalscope/report/utils.py,sha256=DRlbjbqHEmM8rGlA4pwtlHFhOZtyUzcqiS-mejfIDkU,4584
+evalscope/report/utils.py,sha256=uu-rAzoN6ZIlv52IDWSZCcmNVY3DscNo2f9H9-gjZHY,4602
 evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/third_party/longbench_write/README.md,sha256=1yLKeSVIcihpoc4KXr8NpK86JbcLssCPx76aOKdPbYI,5431
 evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u7z6OI79czoBlP8lX4PVo,126
@@ -413,13 +422,14 @@ evalscope/third_party/toolbench_static/config_default.yaml,sha256=-6n6Zyg9eHN2ee
 evalscope/third_party/toolbench_static/eval.py,sha256=do_-lVi_vEoljeLYvt3b_AYSMqpdKzgYnTek9WLSKe8,8236
 evalscope/third_party/toolbench_static/infer.py,sha256=rsADLhEd2IBcC6EI9aD7hSJmo6Oo5b22mnHWBCZLDPs,9010
 evalscope/third_party/toolbench_static/requirements.txt,sha256=OW91Z8hfzh7yQUYgP1Di_E6DgNgGoGP1UcvnqrdCR68,22
-evalscope/third_party/toolbench_static/toolbench_static.py,sha256=ABb9Gy09zMt30tY50AZGxSZ46k3NVEsvuDj6xlLOjeA,1966
+evalscope/third_party/toolbench_static/toolbench_static.py,sha256=xE__eXvSwHmmSh1tXNvyBo6MCO4mDlYTbIYl9OGEfNI,2120
 evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=GITEbyiER10Zi-ZWpSqYCdAsiVtNeGK24hvR3kmYn2s,2689
 evalscope/utils/__init__.py,sha256=jLVoGryuqUh4Km9QWWQBzpqkcVNRK0MbwNaSgckqdiU,139
 evalscope/utils/arena_utils.py,sha256=Gf8VpH4C_oF2Abif_QeL0rAP6tvTzsc0gglpdNkUE48,7155
 evalscope/utils/chat_service.py,sha256=U2jtrkOa2asRp16Zam0zIi_38mCyWQqql_L6JSwii4I,8749
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
+evalscope/utils/deprecation_utils.py,sha256=WyeiLWSi5ti6FkuMbhimcPPUB43paa1FZ5-JOAWNFZI,1344
 evalscope/utils/filters.py,sha256=x_NX40uWMmUsVrAGHCeeV2e63HZZFugWUgdUhk64ivM,1523
 evalscope/utils/import_utils.py,sha256=Oo8saX_mMw4U1RrA7_pn8FmV6P9laru4fEgecqqwpqk,2585
 evalscope/utils/io_utils.py,sha256=Tjdgen1FsAA4ArqiUzu734L0Px5NuiS0GKRRiGIzxSA,4192
@@ -431,11 +441,11 @@ tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
 tests/aigc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/aigc/test_t2i.py,sha256=BcdS3OMypWnraXF4Cq3DhDVRpZq0qo9_0Qpyg54B7FY,2627
 tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/cli/test_all.py,sha256=pwup--iNxckUEsR_aFjIAbEQo3UogSu5aIWf9ryLP2o,4022
-tests/cli/test_collection.py,sha256=y8FjoPziPRf5BdJK8DHjcXn26ETKz1OyqjnCpwjt-F4,4096
-tests/cli/test_run.py,sha256=1DHLFlgGvHJizbLVc1ShcGFAHirEPgW8r88H7g8Sbx4,17245
+tests/cli/test_all.py,sha256=O3lXwOV7A0f0rmltofrjpphnshjNtaZC6NUPG-wsQjg,4082
+tests/cli/test_collection.py,sha256=_11mSCWLaiCgheA3uguv6uI3CxqaHUKVwzS6T5BGmxs,4145
+tests/cli/test_run.py,sha256=FTFiAb8Ge5raB1aa0Nzw8DPjFLyAlLfXHRQVIWjvvGE,17798
 tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=diwwEmoWR-6xSVeGF65J6TWHRNj54rkwyvnhHh7PiE0,3919
+tests/perf/test_perf.py,sha256=VbXsqiqgQY3R3bVKizYQmP04UPluUS26MO6YhTzMs48,4848
 tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 tests/rag/test_clip_benchmark.py,sha256=ZCBtgnF8Vuji6WQlb92-_RIvXlUX_Xt-cHZP4AN_DNI,2552
 tests/rag/test_mteb.py,sha256=YJw6X1jwX6SYNB-ryVb-OHJWu3vsE3Y4STATI75rdG0,5619
@@ -446,9 +456,9 @@ tests/swift/test_run_swift_vlm_eval.py,sha256=C8DftjewnZaerQWfERI70bU3sQLWQ-ejZU
 tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=THZEXUOSqm9rWslwJHmZyh-Ytv5c_QKpgRW5J2s_69E,6017
 tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 tests/vlm/test_vlmeval.py,sha256=UqRiBPMU3vRtLIG1Qu4ZVhyUQx-zGYQuLCgobwf-7a4,3176
-evalscope-0.15.1.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.15.1.dist-info/METADATA,sha256=JvRF5sI_9ak9Y-FwWdU1Y8BE96iKPLO_hIGC7Z9SWpg,34080
-evalscope-0.15.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.15.1.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.15.1.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.15.1.dist-info/RECORD,,
+evalscope-0.16.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-0.16.0.dist-info/METADATA,sha256=zX2L_cLxOjX-NNbiR40dmPOxUWyOH86zJycYjr4j5Po,35492
+evalscope-0.16.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-0.16.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.16.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-0.16.0.dist-info/RECORD,,

tests/cli/test_all.py

@@ -46,6 +46,9 @@ datasets=[
         'alpaca_eval',
         'arena_hard',
         'maritime_bench',
+        'drop',
+        'winogrande',
+        'tool_bench',
 ]
 
 dataset_args={

tests/cli/test_collection.py

@@ -78,7 +78,8 @@ class TestCollection(unittest.TestCase):
                 'model_id': 'qwen2.5-7b-instruct',
                 'api_url': 'https://dashscope.aliyuncs.com/compatible-mode/v1',
                 'api_key': os.getenv('DASHSCOPE_API_KEY'),
-            }
+            },
+            use_cache='outputs/20250519_114427'
         )
         res = run_task(task_cfg=task_cfg)
         print(res)