Video Reasoning on LongVideoReason
73.1AccuracyVideo-Zero
Evaluation Results
| Method | Links | |
|---|---|---|
| Video-ZeroBackbone=MiMo-SFT-7B, Checkpoint=v22026.05 | 73.1 | |
| Video-ZeroBackbone=MiMo-SFT-7B, Checkpoint=v12026.05 | 72.6 | |
| Video-ZeroBackbone=MiMo-SFT-7B, Checkpoint=v32026.05 | 72.5 | |
| Video-ZeroBackbone=InternVL3.5-4B, Checkpoint=v12026.05 | 72 | |
| Video-ZeroBackbone=InternVL3.5-4B, Checkpoint=v22026.05 | 72 | |
| Video-ZeroBackbone=MiMo-SFT-7B, Checkpoint=v42026.05 | 71.8 | |
| Video-ZeroBackbone=InternVL3.5-4B, Checkpoint=v52026.05 | 71.7 | |
| SER-7BParameters=7B2026.06 | 71.7 | |
| Video-ZeroBackbone=InternVL3.5-4B, Checkpoint=v42026.05 | 71.6 | |
| Video-ZeroBackbone=InternVL3.5-4B, Checkpoint=v32026.05 | 71.4 | |
| Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=52026.05 | 71 | |
| Video-Zero (Peak)Backbone=Qwen3-VL-8B-Instruct2026.05 | 71 | |
| Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=42026.05 | 70.7 | |
| Video-Zero (Iter 4)Backbone=Qwen3-VL-8B-Instruct2026.05 | 70.7 | |
| Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=52026.05 | 70.5 | |
| Video-Zero (Peak)Backbone=Qwen3-VL-4B-Instruct2026.05 | 70.5 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=22026.05 | 70.3 | |
| Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=42026.05 | 70.3 | |
| Video-Zero (Iter 4)Backbone=Qwen3-VL-4B-Instruct2026.05 | 70.3 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=22026.05 | 70 | |
| Base ModelBackbone=Qwen3-VL-4B-Instruct2026.05 | 69.9 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=12026.05 | 69.9 | |
| Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=22026.05 | 69.9 | |
| Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=32026.05 | 69.9 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=52026.05 | 69.9 | |
| Base ModelBackbone=Qwen3-VL-4B-Instruct2026.05 | 69.9 | |
| Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=12026.05 | 69.7 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=32026.05 | 69.6 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=42026.05 | 69.6 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=52026.05 | 69.6 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct2026.05 | 69.6 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=12026.05 | 69.5 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=22026.05 | 69.4 | |
| VideoRFT-7BParameters=7B2026.06 | 69.4 | |
| Open-o3-Video2026.06 | 69.4 | |
| VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=52026.05 | 69.3 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=22026.05 | 69.3 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=42026.05 | 69.2 | |
| Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=32026.05 | 69.2 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct2026.05 | 69.2 | |
| MiMo-SFT-7BBackbone=MiMo-SFT-7B, Checkpoint=Base2026.05 | 69.1 | |
| VideoR1-7BParameters=7B2026.06 | 68.9 | |
| Base ModelBackbone=Qwen3-VL-8B-Instruct2026.05 | 68.6 | |
| Base ModelBackbone=Qwen3-VL-8B-Instruct2026.05 | 68.6 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=12026.05 | 68.5 | |
| Video-ZeroBackbone=MiMo-SFT-7B, Checkpoint=v52026.05 | 68.5 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=32026.05 | 68.4 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=32026.05 | 68.4 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=12026.05 | 68.4 | |
| Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=22026.05 | 68.4 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=42026.05 | 68.2 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=52026.05 | 68.2 | |
| V-ZeroBackbone=Qwen3-VL-4B-Instruct2026.05 | 68.2 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=42026.05 | 68.1 | |
| V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=32026.05 | 68.1 | |
| VisPlayBackbone=Qwen3-VL-8B-Instruct2026.05 | 68.1 | |
| Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=12026.05 | 68 | |
| InternVL3.5-4BCheckpoint=Base2026.05 | 68 | |
| InternVL-2.5-8BParameters=8B2026.06 | 62 | |
| VideoLLaMA3-7BParameters=7B2026.06 | 59.8 | |
| Qwen2.5-VL-7BParameters=7B, Model Version=Base model2026.06 | 59.3 |