Video Question Answering on MMVU (val)
68.3Average ScoreKeye-VL-1.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Keye-VL-1.5Model Class=8B2026.05 | 68.3 | — | |
| InternVL-3.5Model Class=8B2026.05 | 60.2 | — | |
| GPT-4o#params=−, #frames=−2026.04 | 60.02 | 75.4 | |
| Qwen3-VLModel Class=8B2026.05 | 58.7 | — | |
| LLaVA-OV-2Model Class=8B2026.05 | 56.2 | — | |
| TTA-Vidbase_model=InternVL-3, #params=8B, #frames=322026.04 | 55.13 | 65.6 | |
| Video-R2#params=7B, #frames=1282026.04 | 53.92 | 67.4 | |
| VideoChat-R1#params=7B, #frames=1282026.04 | 52.34 | 64.8 | |
| Video-RFT#params=7B, #frames=1282026.04 | 52.32 | 66.7 | |
| VideoChat-R1.5#params=7B, #frames=1282026.04 | 52.24 | 67 | |
| Video-R1#params=7B, #frames=1282026.04 | 51.94 | 64 | |
| TTA-Vidbase_model=Qwen2.5-VL, #params=7B, #frames=322026.04 | 51.84 | 65.12 | |
| InternVL-3#params=8B, #frames=322026.04 | 51.37 | 60.8 | |
| TTRV*base_model=Qwen2.5-VL, #params=7B, #frames=322026.04 | 50.46 | 64.48 | |
| LLaVA-OV-1.5Model Class=8B2026.05 | 50.1 | — | |
| Qwen-2.5-VL#params=7B, #frames=<=7682026.04 | 48.82 | 59.2 | |
| PLMModel Class=8B2026.05 | 43.3 | — | |
| LLaVA-OneVision#params=7B, #frames=642026.04 | 43.27 | 49.2 | |
| Random#params=-, #frames=-2026.04 | 17.8 | 20 | |
| Gemini 1.5 Flash#params=−, #frames=−2026.04 | — | 58.8 | |
| Video-RTS#params=7B, #frames=1282026.04 | — | 66.4 |