ultravox-v0.3: benchmark results
Provider: Other.
Aggregate Rating 1532 ± 52, rank #1830 of 10516 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MERA Multi - ruEnvAQA | 38.9 | Score (%) | 68.2 |
| MERA Multi - AQUARIA | 32 | Score (%) | 50 |
| MERA Multi - Audio | 27.9 | Score (%) | 50 |
| MERA Multi - ruTiE-Audio | 28 | Score (%) | 50 |
| MERA Multi - ruSLUn | 12.6 | Score (%) | 45.5 |
| Ambiguous Speech Emotion - IEMOCAP | 0.37 | Jensen-Shannon divergence (0-1; between the emotion distribu | 33.3 |
| Ambiguous Speech Emotion - MSP-Podcast | 0.45 | Jensen-Shannon divergence (0-1; between the emotion distribu | 16.7 |
| Ambiguous Speech Emotion - CREMA-D | 0.44 | Jensen-Shannon divergence (0-1; between the emotion distribu | 0 |
Interactive version: theaggregate.ai/model?slug=ultravox-v0-3 · How It Works · Data refreshed daily, snapshot 2026-11-21.