Visual Mathematical Reasoning on LogicVista
73.8AccuracyGemini-2.5-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.5-Pro2026.01 | 73.8 | |
| GPT-52026.01 | 70 | |
| Doubao-1.5-Pro2026.01 | 64.2 | |
| GLM-4.5V2026.01 | 62.4 | |
| GLM-4.1VModel Size=9B2026.01 | 60.4 | |
| Claude-3.7-Sonnet2026.01 | 58.2 | |
| COGFLOWModel Size=7B2026.01 | 58.1 | |
| InternVL3.5Model Size=8B2026.01 | 57.3 | |
| Keye-VLModel Size=8B2026.01 | 54.8 | |
| Qwen2.5-VLModel Size=8B2026.01 | 44.1 | |
| InternVL3Model Size=8B2026.01 | 44.1 | |
| OvisModel Size=8B2026.01 | 39.4 |