Multimodal Reasoning on LogitVista
52.35Pass@1Masking-KD-4B
Evaluation Results
| Method | Links | |
|---|---|---|
| Masking-KD-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 52.35 | |
| Self-distill Masking-KD-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=4096, Distillation=Self-distill2026.05 | 48.1 | |
| InternVL3-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 47.43 | |
| MiMo-VL-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 46.76 | |
| Qwen2.5-VL-7BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 46.31 | |
| Ovis2-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 43.62 | |
| Qwen3-VL-8B-ThinkingModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 43.4 | |
| Masking-KD-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.05 | 41.61 | |
| Ovis2-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 39.6 | |
| Qwen3-VL-4B-ThinkingModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 39.37 | |
| Qwen2.5-VL-3BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 38.03 | |
| InternVL3.5-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.05 | 37.81 | |
| InternVL3-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 33.33 | |
| Ovis2-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 31.77 | |
| InternVL3.5-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.05 | 27.29 | |
| Qwen3-VL-2B-ThinkingModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 18.57 | |
| InternVL3.5-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.05 | 16.11 |