General Video Understanding on NExT-QA
86.3AccuracyGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.06 | 86.3 | |
| Molmo2-8B2026.06 | 86.2 | |
| VideoChat-Flash-7B2026.06 | 85.5 | |
| Gemini 1.5 ProSource=[60]2026.06 | 85.3 | |
| Eagle-X5-7B2026.06 | 85 | |
| Gemini 1.5 ProSource=[59]2026.06 | 84.3 | |
| Molmo2-O-7B2026.06 | 84.3 | |
| ReMoRa-7B2026.06 | 84.2 | |
| AdaCodecToken budget=comparable, Backbone=Qwen2-VL-7B2026.06 | 84.2 | |
| PLM-7B2026.06 | 84.1 | |
| Qwen2-VL-7B2026.06 | 83.4 | |
| GPT-4o mini2026.06 | 83.2 | |
| LLaVA-Video-7B2026.06 | 83.2 | |
| AdaCodecToken budget=1/7, Backbone=Qwen2-VL-7B2026.06 | 83.1 | |
| CoPE-VideoLM-7B2026.06 | 82.1 | |
| Gemini 1.5 Flash2026.06 | 81.8 | |
| InternVL2-8B2026.06 | 81.7 | |
| GLM-4V-9B2026.06 | 81.3 | |
| Claude 3.5 Sonnet2026.06 | 79.2 | |
| MiniCPM-V-2.6-8B2026.06 | 78.8 | |
| Key-VL-1.5-8B2026.06 | 75.8 |