Video Question Answering on DailyOmni
73.1AccuracyGemini-2.5-Flash
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini-2.5-FlashEvaluation Setting=Direct QA2026.06 | 73.1 | |
| Qwen3-Omni-30B-A3B-InstructEvaluation Setting=Direct QA2026.06 | 71.9 | |
| OmniCaptioner-IF-7BEvaluation Setting=Direct QA2026.06 | 68.4 | |
| video-SALMONN-2-7BEvaluation Setting=Direct QA2026.06 | 66.3 | |
| Qwen2.5-Omni-7BEvaluation Setting=Direct QA2026.06 | 62.1 | |
| ASID-Captioner-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 61.2 | |
| Gemini-2.5-ProEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 60.2 | |
| OmniCaptioner-IF-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 60.2 | |
| GPT-4oEvaluation Setting=Direct QA2026.06 | 56.5 | |
| Gemini-2.5-FlashEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 55.3 | |
| AVoCaDO-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 50.1 | |
| VideoLLaMA2-7BEvaluation Setting=Direct QA2026.06 | 35.2 | |
| video-SALMONN-2-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 29.9 | |
| Qwen3-Omni-Instruct-30B-A3BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 17.5 | |
| UGC-VideoCaptioner-3BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 17 | |
| Qwen2.5-Omni-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 13.4 | |
| MiniCPM-o-2.6-8BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 9.8 | |
| ARC-Hunyuan-Video-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 8.6 | |
| HumanOmniV2-7BEvaluation Protocol=Caption-to-QA, LLM-as-a-judge=Gemini-2.5-Pro2026.06 | 8.2 |