General Audio Understanding on VoiceBench
4.78AlpacaEval Score
GPT-4o-Audio
Updated 5d ago
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.01 | 4.78 | 4.49 | 75.5 | 80.25 | 89.23 | 76.02 | 98.65 | 86.43 | |
2026.01 | 4.5 | 3.84 | 56.4 | 61.7 | 80.9 | 53.5 | 99.2 | 74.04 | |
2026.01 | 4.46 | 3.97 | 63.12 | 62.17 | 83.52 | 61.1 | 100 | 76.93 | |
2026.04 | 4.43 | 3.96 | - | - | 80.9 | - | 98.84 | - | |
2026.04 | 4.33 | 3.84 | - | - | 79.12 | - | 99.62 | - | |
2026.04 | 4.19 | 3.4 | - | - | 66.81 | - | 98.26 | - | |
2026.01 | 4.13 | 3.09 | 44.21 | 28.33 | 33.85 | 27.96 | 69.62 | 49.77 | |
2026.01 | 4.03 | 3.46 | 53.45 | 28.14 | 30.98 | 23.4 | 97.3 | 54.72 | |
2026.01 | 3.97 | 3.42 | 36.98 | 39.75 | 53.41 | 25.92 | 88.08 | 55.99 | |
2026.01 | 3.86 | 3.67 | 40.78 | 38.13 | 61.53 | 40.76 | 85.58 | 59.63 | |
2026.01 | 3.81 | 3.82 | 39.78 | 42.19 | 65.93 | 45.35 | 100 | 63.69 | |
2026.01 | 3.78 | 2.96 | 34.45 | 29.57 | 35.6 | 26.56 | 76.54 | 48.22 | |
2026.01 | 3.74 | 3.43 | 35.72 | 35.72 | 49.45 | 26.33 | 96.73 | 55.34 | |
2026.01 | 3.7 | 3.46 | 39.69 | 25.93 | 27.47 | 14.87 | 11.35 | 37.5 | |
2026.01 | 3.67 | 3.54 | 57.06 | 25.76 | 25.49 | 39.16 | 98.27 | 55.7 | |
2026.01 | 3.38 | 2.15 | 27.94 | 25.7 | 29.01 | 22.82 | 26.73 | 34.68 | |
2026.01 | 2.32 | 2.18 | 9.31 | 24.27 | 26.59 | 11.56 | 57.5 | 31.32 | |
2026.01 | 2.01 | 1.6 | 15.64 | 24.04 | 25.93 | 10.12 | 44.23 | 27.45 | |
2026.01 | 1.9 | 1.79 | 4.16 | 26.06 | 25.27 | 13.38 | 94.23 | 33.84 |