List your company

Grounding & counting on Visual Web Bench

88Pass@1Seed 1.5-VL
79.88881.99484.186.206May 11, 2025

Evaluation results

MethodLinks
Seed 1.5-VLthinking=false, decoding=greedy2025.0588
Seed 1.5-VLthinking=true, decoding=greedy2025.0587.3
Gemini 1.5 Prothinking=true, decoding=greedy2025.0587.3
Claude 3.7 Sonnetthinking=true, decoding=sampling2025.0585.9
Qwen 2.5-VL 72Bthinking=false, decoding=greedy2025.0582.3
OpenAI o1thinking=true, decoding=greedy2025.0580.9
GPT-4othinking=false, decoding=greedy2025.0580.2