Temporal and Textual Video Reasoning on Video-TT MC
46.8AccuracyInsight-V++
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Insight-V++Size=7B, Evaluation Frames=642026.03 | 46.8 | 54.2 | |
| GPT-4oSize=-, Evaluation Frames=642026.03 | 46.6 | 57.8 | |
| Insight-VSize=7B, Evaluation Frames=642026.03 | 45.4 | 52.9 | |
| Oryx-1.5Size=7B, Evaluation Frames=642026.03 | 44.8 | — | |
| InternVL2.5Size=8B, Evaluation Frames=642026.03 | 44.7 | — | |
| VideoChat-R1Size=7B, Evaluation Frames=642026.03 | 42.7 | — | |
| Gemini-1.5-ProSize=-, Evaluation Frames=642026.03 | 42.3 | — | |
| Qwen2.5-VLSize=7B, Evaluation Frames=642026.03 | 42.3 | 47.3 | |
| LLaVA-VideoSize=7B, Evaluation Frames=642026.03 | 41.8 | — |