Multimodal Reasoning on Geo3k
62.23Pass@1MiMo-VL-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| MiMo-VL-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 62.23 | |
| Self-distill Masking-KD-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=4096, Distillation=Self-distill2026.05 | 58.24 | |
| Qwen3-VL-8B-ThinkingModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 54.58 | |
| Masking-KD-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 52.58 | |
| InternVL3.5-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 44.59 | |
| Qwen3-VL-4B-ThinkingModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 43.93 | |
| Ovis2-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 42.43 | |
| InternVL3.5-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 41.93 | |
| Masking-KD-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 40.93 | |
| Qwen2.5-VL-7BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 40.43 | |
| InternVL3-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 38.44 | |
| Ovis2-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 37.77 | |
| InternVL3-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 33.78 | |
| Ovis2-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 31.11 | |
| InternVL3.5-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 29.95 | |
| Qwen2.5-VL-3BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 26.29 | |
| Qwen3-VL-2B-ThinkingModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 26.29 |