List your company

General Reasoning on AI2D

84.1AccuracyQwen3-VL-8B
59.368865.789472.2178.6306May 12, 2026May 13, 2026May 14, 2026May 15, 2026May 16, 2026May 17, 2026May 19, 2026

Evaluation results

MethodLinks
Qwen3-VL-8BMode=base2026.0584.1
S^3-FTBackbone=Qwen3-VL-8B, Mode=Single-view2026.0583.6
S^3-FTBackbone=Qwen3-VL-8B, Mode=Cross-viewpoint2026.0582.6
Qwen2.5-VL-7BMode=base2026.0580.9
S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Single-view2026.0580.9
S^3-FTBackbone=Qwen2.5-VL-7B, Mode=Cross-viewpoint2026.0580.6
NashStrategy=Step-wise verification2026.0578.95
LLaVA CriticStrategy=Step-wise verification2026.0576.61
BaseStrategy=Step-wise verification2026.0576.52
SherlockStrategy=Step-wise verification2026.0561.54
VisionSR1Strategy=Step-wise verification2026.0560.32