Benchmark
VoiceBench CommonEval
Scores are percentages.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 3.9%
- Mean
- 3.8%
- Median
- 0.575%
- Std dev
- 3.1%
- 10th percentile
- 4.5%
- 90th percentile
- 3.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | qwen3-omni-30b-a3b-instruct· VoiceBench | 4.5% |
| 2 | Qwen3 Omni 30B A3B Thinking· VoiceBench | 4.5% |
| 3 | Phi 4 Multimodal Instruct· VoiceBench | 3.8% |
| 4 | GLM-4-Voice· VoiceBench | 3.4% |
| 5 | Nemotron 3 VoiceChatV1· VoiceBench | 3.1% |
Data credits: VoiceBench (NUS HLT Lab), Apache-2.0 (licence)