Multimodal Mathematical Reasoning on MathVerse Vision-only 35
85.91Macro Avg ScoreGemini-3-Pro*
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Gemini-3-Pro*Model Type=Closed-source LMM2026.05 | 85.91 | — | — | — | — | |
| Qwen3VL-8B-instruct + GeoSym EntryBase Model=Qwen3-VL, Parameter Scale=8B, Method Component=GeoSym Entry2026.05 | 60.53 | 62.69 | 75.83 | 51.65 | 65.29 | |
| Qwen3VL-8B-instruct + GeoSym HardBase Model=Qwen3-VL, Parameter Scale=8B, Method Component=GeoSym Hard2026.05 | 60.41 | 65.28 | 72.53 | 51.65 | 65.49 | |
| Qwen3VL-8B-instructBase Model=Qwen3-VL, Parameter Scale=8B2026.05 | 38.32 | 36.27 | 40.66 | 25.27 | 38.04 |