Omni-modal reasoning on DailyOmni (test)
67.8ScoreGemini-2.0-Flash
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-2.0-Flash2026.02 | 67.8 | |
| ThinkOmniBase Model=Omni-R1-7B, LRM Guide=DeepSeek2026.02 | 60.3 | |
| ThinkOmniBase Model=Qwen2.5-Omni-7B, LRM Guide=DeepSeek2026.02 | 59.8 | |
| ThinkOmniBase Model=Omni-R1-7B, LRM Guide=Qwen32026.02 | 59.8 | |
| Omni-R1Notes=Evaluated using authors' scripts2026.02 | 59.6 | |
| Omni-R12026.02 | 59.6 | |
| ThinkOmniBase Model=Qwen2.5-Omni-7B, LRM Guide=Qwen32026.02 | 59.5 | |
| HumanOmniV2Notes=Evaluated using authors' scripts2026.02 | 58.5 | |
| Qwen2.5-Omni-7B2026.02 | 57.9 | |
| ThinkOmniBase Model=Qwen2.5-Omni-3B, LRM Guide=Qwen32026.02 | 57.3 | |
| ThinkOmniBase Model=Qwen2.5-Omni-3B, LRM Guide=DeepSeek2026.02 | 57.1 | |
| Qwen2.5-Omni-3B2026.02 | 56.6 | |
| GPT-4o2026.02 | 56.5 | |
| Ola2026.02 | 50.71 | |
| Baichuan-Omni-1.52026.02 | 50 |