ultravox-v0.5-llama-3.1-8B: benchmark results
Provider: Other.
Aggregate Rating 1531 ± 47, rank #1935 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CBT-Audio (Audio + Transcript) | 0.9 | Mean absolute error on the 1-5 distress-intensity scale agai | 77.8 |
| CBT-Audio (Audio Only) | 0.91 | Mean absolute error on the 1-5 distress-intensity scale agai | 77.8 |
| CBT-Audio (Transcript Only) | 0.88 | Mean absolute error on the 1-5 distress-intensity scale agai | 77.8 |
| MERA Multi - ruSLUn | 23.1 | Score (%) | 77.3 |
| MERA Multi - AQUARIA | 33.8 | Score (%) | 68.2 |
| MERA Multi - Audio | 31.1 | Score (%) | 68.2 |
| MERA Multi - ruTiE-Audio | 30 | Score (%) | 61.4 |
| MERA Multi - ruEnvAQA | 37.5 | Score (%) | 50 |
Interactive version: theaggregate.ai/model?slug=ultravox-v0-5-llama-3-1-8b · How It Works · Data refreshed daily, snapshot 2026-11-08.