src/multi_modal_results.csv

Rank,Agent,VLMs,Score,Pass Rate,Total Input Tokens,Total Output Tokens,All Tokens
1,ZoomEye,Qwen2.5-VL-72B-Instruct,51.56,0.9981,76808965,1276460,78085425
2,ZoomEye,Qwen2.5-VL-7B-Instruct,48.06,0.965,94418593,1472836,95891429
3,IO,Qwen2.5-VL-72B-Instruct,44.47,1.0,6174490,2114,6176604
4,ZoomEye,InternVL2.5-8B,43.42,0.9934,153857588,2017170,155874758
5,IO,InternVL2.5-8B,42.95,1.0,2779778,2335,2782113
6,IO,Qwen2.5-VL-7B-Instruct,42.86,1.0,6174490,2114,6176604
7,ZoomEye,Llava-v1.5-7B,31.6,0.9886,113073261,1368724,114441985
8,IO,Llava-v1.5-7B,24.79,1.0,734868,17036,751904
9,V*,seal_vqa & seal_vsm,15.14,0.7237,0,0,0