Audio Classification on AudioMarathon 1.0 (test)
78.4SED ScoreQwen2.5-Omni-7B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen2.5-Omni-7BParameters=7B2026.02 | 78.4 | 100 | 72.2 | |
| Voxtral-Mini-3B-2507Parameters=3B, Version=25072026.02 | 71 | 83.8 | 27.2 | |
| Qwen2.5-Omni-3BParameters=3B2026.02 | 70.2 | 97.4 | 69.3 | |
| Gemini-2.5-Flash2026.02 | 69.2 | 79.3 | 40.8 | |
| Gemini-2.5-Flash-Lite2026.02 | 68 | 64.8 | 36.8 | |
| Audio-Flamingo-32026.02 | 59.5 | 97 | 54.1 | |
| Phi-4-Multimodal2026.02 | 55.1 | 46.7 | 23.4 | |
| Aero-1-Audio2026.02 | 55 | 83.9 | 39.9 | |
| Speech-XL2026.02 | 53.4 | 40.4 | 24.3 | |
| GPT-4o-Audio (2024-12-17)Release Date=2024-12-172026.02 | 51.2 | 67.6 | 41.9 | |
| GPT-4o-Audio (2024-10-01)Release Date=2024-10-012026.02 | 50.7 | 59.5 | 40.8 | |
| Gemma-3n-E4B-itModel Size=4B2026.02 | 50.2 | 71.9 | 31.7 | |
| Gemma-3n-E2B-itModel Size=2B2026.02 | 50.2 | 56.8 | 28.2 | |
| Baichuan-Omni-1.52026.02 | 45.7 | 52 | 25.8 | |
| Audio-Flamingo-22026.02 | 27.1 | 66.8 | 29.7 |