Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Grounding & counting on Visual Web Bench
Loading...
88
Pass@1
Seed 1.5-VL
79.888
81.994
84.1
86.206
May 11, 2025
Pass@1
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Seed 1.5-VL
thinking=false, decodi...
2025.05
88
Seed 1.5-VL
thinking=true, decodin...
2025.05
87.3
Gemini 1.5 Pro
thinking=true, decodin...
2025.05
87.3
Claude 3.7 Sonnet
thinking=true, decodin...
2025.05
85.9
Qwen 2.5-VL 72B
thinking=false, decodi...
2025.05
82.3
OpenAI o1
thinking=true, decodin...
2025.05
80.9
GPT-4o
thinking=false, decodi...
2025.05
80.2
Feedback
Search any
task
Search any
task