Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Diagram Understanding on AI2D (Pass@1 accuracy)
Loading...
86.5
Pass@1 Accuracy
Qwen2.5-VL-7B-Instruct + cold start
77.868
80.109
82.35
84.591
Apr 11, 2026
Pass@1 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Qwen2.5-VL-7B-Instruct + cold start
Model Source Category=...
2026.04
86.5
InternVL2.5-26B
Model Source Category=...
2026.04
86.4
LLaVA-OneVision-72B
Model Source Category=...
2026.04
85.6
GPT-4o-20240513
Model Source Category=...
2026.04
84.6
InternVL3-9B
Model Source Category=...
2026.04
84.6
InternVL2.5-8B
Model Source Category=...
2026.04
84.5
Qwen2.5-VL-7B-Instruct + RFT
Model Source Category=...
2026.04
84.1
Qwen2.5-VL-7B-Instruct
Model Source Category=...
2026.04
83.9
Qwen2.5-VL-7B-Instruct
Model Source Category=...
2026.04
83.9
Qwen2.5-VL-7B-Instruct
Model Source Category=...
2026.04
83.1
Qwen2-VL-7B
Model Source Category=...
2026.04
83
MiniCPM-V2.6
Model Source Category=...
2026.04
82.1
Claude-3.5-Sonnet
Model Source Category=...
2026.04
81.2
Cambrian-34B
Model Source Category=...
2026.04
79.5
Gemini-1.5-Pro
Model Source Category=...
2026.04
79.1
GPT-4V
Model Source Category=...
2026.04
78.2
Feedback
Search any
task
Search any
task