Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
VP-QA on ProcedureVQA
Loading...
62.5
Accuracy
GPT-4o
23.604
33.702
43.8
53.898
May 14, 2026
Accuracy
Updated 2mo ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-4o
Prompting Strategy=Zer...
2026.05
62.5
Claude-3-5-Sonnet
Prompting Strategy=CoT
2026.05
55.6
GPT-4o
Prompting Strategy=CoT
2026.05
51.8
Claude-3-5-Sonnet
Prompting Strategy=Zer...
2026.05
47.5
Gemini-2.5-Flash
Prompting Strategy=Zer...
2026.05
44.7
Qwen2.5-VL-72B
Prompting Strategy=Zer...
2026.05
43.4
GPT-4o-mini
Prompting Strategy=CoT
2026.05
42.7
Gemini-2.5-Flash
Prompting Strategy=CoT
2026.05
42.6
Qwen2.5-VL-72B
Prompting Strategy=CoT
2026.05
41.3
GPT-4o-mini
Prompting Strategy=Zer...
2026.05
34.4
Qwen2.5-VL-7B
Prompting Strategy=CoT
2026.05
26.6
Qwen2.5-VL-7B
Prompting Strategy=Zer...
2026.05
25.1
Feedback
Search any
task
Search any
task