Multimodal Reasoning on MathVista (Pass@1)
69.5Pass@1MiMo-VL-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| MiMo-VL-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 69.5 | |
| InternVL3.5-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 68.5 | |
| Ovis2-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 68.2 | |
| Qwen2.5-VL-7BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 67.5 | |
| Self-distill Masking-KD-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=4096, Distillation=Self-distill2026.05 | 67.1 | |
| Masking-KD-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 66.5 | |
| Qwen3-VL-8B-ThinkingModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 65.2 | |
| Qwen3-VL-4B-ThinkingModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 62.6 | |
| Ovis2-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 61.1 | |
| Masking-KD-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 59.2 | |
| Qwen2.5-VL-3BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 55.9 | |
| Ovis2-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 54.7 | |
| InternVL3-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 53.2 | |
| InternVL3.5-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 52.1 | |
| InternVL3-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 46.7 | |
| Qwen3-VL-2B-ThinkingModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 43.1 | |
| InternVL3.5-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 40.6 |