Audio Understanding Benchmark (Mistral)
Voxtral Small 86.6% Models answer hard questions about 40 long-form audio recordings. Mistral built it in-house to test audio understanding beyond transcription.
Mistral reported it once, as a chart without printed values, in the Voxtral launch post. The grading method is not described, so model-judged is assumed.
- Made by
- Mistral AI
- Released
- July 2025
- Kind
- Audio understanding and voice
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Short answer
- Tasks
- Kept private
- Last in a launch post
- July 2025, dropped before it saturated
- Last model added
- July 2025
Voxtral Small leads with 86.6%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Voxtral Small 86.6%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Voxtral Small | 86.6% | Jul 2025 | Lab model card |
Mistral AI’s own number for Voxtral Small passed 85% in July 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
No launch post has listed it since July 2025
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Jul 15, 2025 | Voxtral Small | AU Benchmark, 40 long-form audio examples (chart) |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Jul 17, 2025 | Voxtral Small technical report | 86.6 | AU Bench, internal speech understanding benchmark, LLM judge score (Table 8). SFT default checkpoint 86.61 with grade 4.16 of 5 (Table 2) | Capabilities |
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7% - LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7% - MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00% - VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%