Audio-visual understanding on VideoHolmes
67AccuracyGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProModel access type=Closed-source2026.02 | 67 | |
| Gemini-2.5-ProModel access type=Closed-source2026.02 | 64.9 | |
| OmniVideo-R1Model access type=Open-source2026.02 | 62.9 | |
| video-SALMONN 2+-72BModel access type=Open-source2026.02 | 57.8 | |
| Qwen3-Omni-30B-A3B-ThinkingModel access type=Open-source2026.02 | 57.3 | |
| Qwen3-Omni-30B-A3B-InstructModel access type=Open-source2026.02 | 49 | |
| video-SALMONN 2+-7BModel access type=Open-source2026.02 | 46.9 | |
| VideoLLaMA2-7BModel access type=Open-source2026.02 | 35.2 | |
| Gemini-2.0-FlashModel access type=Closed-source2026.02 | 30.6 | |
| Qwen2.5-Omni-7BModel access type=Open-source2026.02 | 16.4 |