1,133
±164 95% CI
57%
Win rate
21
Battles
AudioLab Leaderboards
Pairwise preference rankings and independent benchmarks for leading speech models.
Valid votes
67
Models
6
Method
Bradley–Terry MLE
Speech to Text rankings
Models are ordered by rating. Models are marked preliminary until 200 valid battles; disabled models are hidden. Newly added models appear unranked at the bottom until they record their first battles.
Controls only for which response was heard first.
Preliminary models have fewer than the required valid battles or a weakly connected matchup graph. Treat their rank and confidence interval as directional.
1,113
±160 95% CI
54%
Win rate
34
Battles
1,090
±153 95% CI
50%
Win rate
31
Battles
1,041
±144 95% CI
44%
Win rate
18
Battles
1,000
±0 95% CI
35%
Win rate
30
Battles
—
—
Win rate
0
No battles yet
Performance by language
Win rate per language. Cells with too few battles are left blank.
| Model | English |
|---|---|
| Mistral Voxtral Small | 52% |
| OpenAI GPT-4o Audio | 52% |
| Alibaba Qwen3-Omni Flash | 36% |