Datasets:

Med2026
/

Med_eval_data

license: mit
task_categories:
  - visual-question-answering
  - image-text-to-text
language:
  - en
pretty_name: Med Eval Data
size_categories:
  - 10K<n<100K

Med Eval Data

This dataset contains evaluation data for the Med project. Its data format is the same as Med2026/Med_training_data, and it can be loaded with the same codebase from GAIR-NLP/Med.

Overview

Each example is stored in the same JSON / parquet schema as the training data, with the following top-level fields:

images
data_source
prompt
ability
reward_model
extra_info
agent_name

This means the dataset is directly compatible with the data loading pipeline used in the Med codebase.

Compatibility

This dataset has the same format as Med2026/Med_training_data.

You can use the same loading logic and preprocessing pipeline from:

GAIR-NLP/Med

No format conversion is required.

Data Split by File Naming

The evaluation data is divided into two settings according to the file name:

Files with single_turn_agent in the filename correspond to evaluation without tool use
Files with tool_agent in the filename correspond to evaluation with tool use

In other words:

*single_turn_agent* → without-tool evaluation
*tool_agent* → with-tool evaluation

Data Format

Each sample is a JSON object with the following structure:

{
  "images": [PIL.Image],
  "data_source": "vstar_bench_single_turn_agent",
  "prompt": [
    {
      "content": "<image>\nWhat is the material of the glove?\n(A) rubber\n(B) cotton\n(C) kevlar\n(D) leather\nAnswer with the option's letter from the given choices directly.",
      "role": "user"
    }
  ],
  "ability": "direct_attributes",
  "reward_model": {
    "answer": "A",
    "format_ratio": 0.0,
    "ground_truth": "\\boxed{A}",
    "length_ratio": 0.0,
    "style": "multiple_choice",
    "verifier": "mathverify",
    "verifier_parm": {
      "det_verifier_normalized": null,
      "det_reward_ratio": {
        "iou_max_label_first": null,
        "iou_max_iou_first": null,
        "iou_completeness": null,
        "map": null,
        "map50": null,
        "map75": null
      }
    }
  },
  "extra_info": {
    "answer": "A",
    "data_source": "vstar_bench_single_turn_agent",
    "id": "vstar_bench_0",
    "image_path": "direct_attributes/sa_4690.jpg",
    "question": "<image>\nWhat is the material of the glove?\n(A) rubber\n(B) cotton\n(C) kevlar\n(D) leather\nAnswer with the option's letter from the given choices directly.",
    "split": "test",
    "index": "0",
    "prompt_length": null,
    "tools_kwargs": {
      "crop_and_zoom": {
        "create_kwargs": {
          "raw_query": "What is the material of the glove?\n(A) rubber\n(B) cotton\n(C) kevlar\n(D) leather\nAnswer with the option's letter from the given choices directly.",
          "image": "PIL.Image"
        }
      }
    },
    "need_tools_kwargs": false
  },
  "agent_name": "single_turn_agent"
}