Mathematical Reasoning on MathVista 96 (testmini)
89.1ScoreGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 ProModel Category=API call only2026.01 | 89.1 | |
| Gemini 2.5 ProModel Category=API call only2026.01 | 84.6 | |
| GPT-5Model Category=API call only2026.01 | 82.7 | |
| Gemini 2.5 FlashModel Category=API call only2026.01 | 81.2 | |
| Keye-VL-1.5-8BModel Category=Open weights only2026.01 | 81.2 | |
| GLM-4.1V-9BModel Category=Open weights only2026.01 | 80.7 | |
| MiniCPM-V-4.5-8BModel Category=Open weights only2026.01 | 79.9 | |
| GPT-5 miniModel Category=API call only2026.01 | 79.2 | |
| InternVL3.5-8BModel Category=Open weights only2026.01 | 78.4 | |
| Qwen3-VL-8BModel Category=Open weights only2026.01 | 77.2 | |
| InternVL3.5-4BModel Category=Open weights only2026.01 | 77.1 | |
| Qwen3-VL-4BModel Category=Open weights only2026.01 | 73.7 | |
| Claude Sonnet 4.5Model Category=API call only2026.01 | 73.1 | |
| Eagle2.5-8BModel Category=Open weights only2026.01 | 67.8 | |
| PLM-8BModel Category=Open models2026.01 | 59.9 | |
| PLM-3BModel Category=Open models2026.01 | 59.1 | |
| Molmo2-8BModel Category=Molmo2 family2026.01 | 58.9 | |
| Molmo-72BModel Category=Molmo1 family2026.01 | 58.6 | |
| Molmo2-4BModel Category=Molmo2 family2026.01 | 56.7 | |
| Molmo2-O-7BModel Category=Molmo2 family2026.01 | 54.2 | |
| Molmo-7B-DModel Category=Molmo1 family2026.01 | 51.6 | |
| Molmo-7B-OModel Category=Molmo1 family2026.01 | 44.5 | |
| MolmoE-1BModel Category=Molmo1 family2026.01 | 34 |