Short-video Question Answering on Short-video QA Suite
86.3NextQA AccuracyGPT-5
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GPT-5Model Category=Proprietary2026.06 | 86.3 | 79.4 | 74.1 | 53 | 65.4 | 80.4 | 73.1 | |
| VideoChat-Flash-7BModel Category=Open-Weight2026.06 | 85.5 | 76.5 | 74 | 32.5 | 60.6 | 69.4 | 66.4 | |
| InternVideo3Model Category=Open-Weight2026.06 | 85.5 | 81.4 | 75 | 37.4 | 60.6 | 74 | 69 | |
| Gemini 2.5 ProModel Category=Proprietary2026.06 | 85.3 | 78.4 | 70.6 | 48.6 | 62 | 81.9 | 71.1 | |
| Eagle2.5-8BModel Category=Open-Weight2026.06 | 85 | 81 | 74.8 | 31 | 55.7 | 74.4 | 67 | |
| InternVideo2.5-7BModel Category=Open-Weight2026.06 | 84.9 | 74.9 | 75.7 | 32.9 | 60.8 | 70.1 | 66.5 | |
| Gemini 3 ProModel Category=Proprietary2026.06 | 84.3 | 77.6 | 70.4 | 48.3 | 62.6 | 82.8 | 71 | |
| Qwen3-VL-8BModel Category=Open-Weight2026.06 | 83.4 | 72.7 | 68.7 | 35.7 | 56.9 | 74.3 | 65.3 | |
| GPT-5 miniModel Category=Proprietary2026.06 | 83.2 | 72 | 66.5 | 44.1 | 59.9 | 74.9 | 66.8 | |
| LLaVA-Video-7BModel Category=Open-Weight2026.06 | 83.2 | 68.8 | 58.6 | 24.9 | 54.2 | 66.6 | 59.4 | |
| Gemini 2.5 FlashModel Category=Proprietary2026.06 | 81.8 | 74.7 | 67 | 39.1 | 59.3 | 80.2 | 67 | |
| InternVL3.5-8BModel Category=Open-Weight2026.06 | 81.7 | 72.7 | 72.1 | 24.6 | 56.6 | 70.3 | 63 | |
| GLM-4.1V-9BModel Category=Open-Weight2026.06 | 81.3 | 74.2 | 68.4 | 30 | 59 | 72.3 | 64.2 | |
| Claude Sonnet 4.5Model Category=Proprietary2026.06 | 79.2 | 64.3 | 62.1 | 39.6 | 58.5 | 72.8 | 62.8 | |
| MiniCPM-V-4.5-8BModel Category=Open-Weight2026.06 | 78.8 | 70.9 | 60.5 | 29.8 | 59.7 | 72.7 | 62.1 | |
| Keye-VL-1.5-8BModel Category=Open-Weight2026.06 | 75.8 | 64.2 | 56.9 | 33 | 55.1 | 75.5 | 60.1 |