Geometric Reasoning on Geometry3K (avg@8 accuracy)
44.11Avg@8 AccuracyPAPO_D
Evaluation Results
| Method | Links | |
|---|---|---|
| PAPO_DBackbone=Qwen2.5-VL, Model Size=7B, Training Algorithm=PAPO_D, Inference Temperature=1.02025.07 | 44.11 | |
| PAPO_GBackbone=Qwen3-VL (thinking), Model Size=2B, Training Algorithm=PAPO_G, Inference Temperature=1.02025.07 | 41.08 | |
| PAPO_GBackbone=Qwen2.5-VL, Model Size=7B, Training Algorithm=PAPO_G, Inference Temperature=1.02025.07 | 40.25 | |
| GRPOBackbone=Qwen2.5-VL, Model Size=7B, Training Algorithm=GRPO, Inference Temperature=1.02025.07 | 40.18 | |
| GRPOBackbone=Qwen3-VL (thinking), Model Size=2B, Training Algorithm=GRPO, Inference Temperature=1.02025.07 | 39.29 | |
| DAPOBackbone=Qwen2.5-VL, Model Size=7B, Training Algorithm=DAPO, Inference Temperature=1.02025.07 | 35.92 | |
| PAPO_DBackbone=Qwen2.5-VL, Model Size=3B, Training Algorithm=PAPO_D, Inference Temperature=1.02025.07 | 35.65 | |
| DAPOBackbone=Qwen2.5-VL, Model Size=3B, Training Algorithm=DAPO, Inference Temperature=1.02025.07 | 31.2 | |
| PAPO_GBackbone=Qwen2.5-VL, Model Size=3B, Training Algorithm=PAPO_G, Inference Temperature=1.02025.07 | 30.95 | |
| GRPOBackbone=Qwen2.5-VL, Model Size=3B, Training Algorithm=GRPO, Inference Temperature=1.02025.07 | 28.72 |