Video Hallucination Assessment on VideoHallucer
95.1AccuracyVideo-LLaVA
Evaluation Results
| Method | Links | |
|---|---|---|
| Video-LLaVA2026.05 | 95.1 | |
| LLaVA-OV2026.05 | 84.1 | |
| Gemini-1.5-Pro2026.05 | 83.6 | |
| STEMO-TrackBackbone=Gemini-3-Flash2026.05 | 83.5 | |
| STEMO-TrackBackbone=Qwen3-VL-235B2026.05 | 80.6 | |
| GPT-4o2026.05 | 75.1 | |
| Gemini-3-Flash2026.05 | 66.8 | |
| GPT-4oCategory=Closed-source2026.01 | 53.3 | |
| Qwen-VL-2.5-7B-OursCategory=Our Models2026.01 | 50.8 | |
| InternVL2.5-8BCategory=Open-source Base Models2026.01 | 50.5 | |
| MiniCPM-V2.6-8BCategory=Open-source Base Models2026.01 | 48.4 | |
| Qwen-VL-2.5-7BCategory=Our Models2026.01 | 46.5 | |
| Video-R1-7BCategory=Open-source Reasoning Models2026.01 | 45.1 | |
| LLaVA-OneVision-7BCategory=Open-source Video Models2026.01 | 44.6 | |
| Vision-R1-7BCategory=Open-source Reasoning Models2026.01 | 44.2 | |
| R1-VL-7BCategory=Open-source Reasoning Models2026.01 | 43.6 | |
| Qwen-VL-2.5-7B-SFTCategory=Our Models2026.01 | 43.5 | |
| R1-OneVision-7BCategory=Open-source Reasoning Models2026.01 | 42.4 | |
| Qwen-VL-2.5-7B-GRPOCategory=Our Models2026.01 | 42.3 | |
| Gemini-1.5-ProCategory=Closed-source2026.01 | 37.8 | |
| Qwen3.5-27B2026.05 | 36.1 | |
| VideoChat22026.05 | 29.7 | |
| VILA-1.5-8BCategory=Open-source Video Models2026.01 | 14.8 |