Mathematical Reasoning on Geometry3k
79.9AccuracyGPT-5-Thinking*
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-5-Thinking*Model Category=Close-source, Reference Source=OpenCompass leaderboard2025.09 | 79.9 | — | |
| GPT-5-Thinking*Model Category=Closed-Source Models2026.04 | 79.9 | 84.3 | |
| Gemini-2.5-Pro*Model Category=Close-source, Reference Source=OpenCompass leaderboard2025.09 | 77.2 | — | |
| Gemini-2.5-Pro*Model Category=Closed-Source Models2026.04 | 77.2 | 80.1 | |
| V-STARData Size=40k2026.04 | 69.4 | — | |
| ThinkLite-VLData Size=11k2026.04 | 68.9 | — | |
| VL-CogitoData Size=80k2026.04 | 68.7 | — | |
| VL-RethinkerData Size=39k2026.04 | 67.7 | — | |
| Vision-R1Data Size=210k2026.04 | 67 | — | |
| OpenVLThinkerData Size=59.2k2026.04 | 60.6 | — | |
| Qwen2.5VL2026.04 | 59.2 | — | |
| R1-OnevisionData Size=155k2026.04 | 57.9 | — | |
| MUPO-Thinker-7BModel Category=Our Models2026.04 | 52.1 | 59.1 | |
| VAPO-Thinker-7BModel Category=Our models, Parameter Scale=7B2025.09 | 51.3 | — | |
| VLAA-Thinker-7BModel Category=Open-source, Parameter Scale=7B2025.09 | 50.6 | — | |
| VLAA-Thinker-7BModel Category=Open-Source Models2026.04 | 50.6 | 55.2 | |
| Vision-R1-7BModel Category=Open-source, Parameter Scale=7B2025.09 | 49 | — | |
| Vision-R1-7BModel Category=Open-Source Models2026.04 | 49 | 54.1 | |
| R1-OneVision-7BModel Category=Open-source, Parameter Scale=7B2025.09 | 46.1 | — | |
| R1-OneVision-7BModel Category=Open-Source Models2026.04 | 46.1 | 50.4 | |
| MUPO-Thinker-3BModel Category=Our Models2026.04 | 45.1 | 52.9 | |
| InternVL2.5-8B*Model Category=Open-source, Parameter Scale=8B, Reference Source=OpenCompass leaderboard2025.09 | 44.8 | — | |
| InternVL2.5-8B*Model Category=Open-Source Models2026.04 | 44.8 | 48 | |
| VAPO-Thinker-3BModel Category=Our models, Parameter Scale=3B2025.09 | 44.2 | — | |
| Qwen2.5-VL-7BModel Category=Open-source, Parameter Scale=7B2025.09 | 38.5 | — | |
| Qwen2.5-VL-7BModel Category=Open-Source Models2026.04 | 38.5 | 54.4 |