static/eval_results/Default/self_reported.json

{
    "MiniMax-VL-01": 47.4,
    "Qwen2.5-VL-72B": 51.3,
    "Qwen2.5-VL-7B": 36.8,
    "Qwen2.5-VL-3B": 28.9,
    "GPT-o1": 58.0,
    "GPT-o1-mini": 54.2
}