Video Question Answering on Video-BrowseComp 1.0 (test)
26.19OAVideoBrowser (GPT-5.1)
Evaluation Results
| Method | Links | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| VideoBrowser (GPT-5.1)Backbone=GPT-5.1, Model Category=Video Browser, Pyramidal Perception=True2025.12 | 26.19 | 37.6 | 11.29 | 4.35 | 44.6 | 10 | 40 | 31.15 | 4.55 | 20 | 20 | 26.32 | 44.44 | |
| gemini-2.5-pro (S)Web Search Capability=True, Model Category=Search Models2025.12 | 23.81 | 37.6 | 4.84 | 0 | 31.45 | 20 | 32 | 31.15 | 9.09 | 10 | 8.89 | 57.89 | 16.67 | |
| o4-mini-deep-researchWeb Search Capability=True, Model Category=Search Models2025.12 | 22.86 | 30.4 | 12.9 | 8.7 | 42.55 | 10 | 28 | 29.51 | 27.27 | 10 | 17.78 | 21.05 | 16.67 | |
| gemini-2.5-flash (S)Web Search Capability=True, Model Category=Search Models2025.12 | 20.95 | 32.8 | 4.84 | 0 | 35.98 | 0 | 36 | 29.51 | 4.55 | 10 | 11.11 | 36.84 | 16.67 | |
| gemini-2.5-proWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 19.52 | 31.2 | 3.23 | 0 | 79.18 | 10 | 28 | 29.51 | 13.64 | 0 | 2.22 | 36.84 | 22.22 | |
| VideoBrowser (Qwen3)Backbone=Qwen3, Model Category=Video Browser, Pyramidal Perception=True2025.12 | 19.05 | 25.6 | 9.68 | 8.7 | 69.81 | 0 | 36 | 22.95 | 4.55 | 10 | 11.11 | 15.79 | 38.89 | |
| gpt-4o-2024Web Search Capability=False, Model Category=Tool-Free Models2025.12 | 17.62 | 28 | 3.23 | 0 | 58.81 | 10 | 16 | 26.23 | 13.64 | 0 | 4.44 | 31.58 | 27.78 | |
| gemini-2.5-flashWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 16.67 | 27.2 | 1.61 | 0 | 77.79 | 20 | 20 | 24.59 | 4.55 | 0 | 2.22 | 36.84 | 22.22 | |
| gpt-5-miniWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 15.71 | 26.4 | 0 | 0 | 37.47 | 0 | 28 | 22.95 | 13.64 | 10 | 0 | 21.05 | 22.22 | |
| gpt-5.1 (S)Web Search Capability=True, Model Category=Search Models2025.12 | 15.24 | 21.6 | 6.45 | 4.35 | 30.2 | 0 | 8 | 21.31 | 18.18 | 10 | 8.89 | 21.05 | 22.22 | |
| Qwen3-VL-235B-InsWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 13.33 | 22.4 | 0 | 0 | 77.64 | 0 | 12 | 19.67 | 13.64 | 0 | 2.22 | 21.05 | 27.78 | |
| GLM-4.6VWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 10.95 | 16.8 | 3.23 | 0 | 44.4 | 0 | 12 | 11.48 | 13.64 | 10 | 2.22 | 26.32 | 16.67 | |
| gpt-4o-miniWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 9.52 | 16 | 0 | 0 | 63.55 | 0 | 12 | 18.03 | 9.09 | 0 | 0 | 15.79 | 5.56 | |
| Qwen3-VL-8B-ThinkWeb Search Capability=False, Model Category=Tool-Free Models2025.12 | 7.14 | 12 | 0 | 0 | 52.49 | 10 | 0 | 13.11 | 0 | 20 | 0 | 5.26 | 16.67 |