Acoustic attribute perception and articulation on Step-Caption
75.55Overall ScoreGemini 3 Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini 3 Pro2026.04 | 75.55 | |
| qwen3.5-omni-plus2026.04 | 74.93 | |
| qwen3.5-omni-flash2026.04 | 73.57 | |
| Step-Audio-R1.52026.04 | 71.48 | |
| Step-Audio-R12026.04 | 70.6 | |
| Gemini 3 Flash2026.04 | 65.12 |