Data as of October 20, 2026 · How the score is built
Released Oct 20, 202632K contextMistral AI model documentation
Voxtral Mini Transcribe 3
Decision readingVoxtral Mini Transcribe 3 is tracked, but not publicly ranked yet. Published speech or voice results from Voxtral 3 launch evaluation appear below. They do not produce a weighted text-model score.
Released Oct 20, 2026 — see all recent releases
Voice benchmark evidence
Voxtral 3 launch evaluation is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- voxtral-mini-transcribe-3-0Mistral AI model documentation
- Context window
- 32KMistral AI model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Released October 20, 2026 as a public preview in the Mistral API as `voxtral-mini-transcribe-3-0`. Mistral reports 4B parameters and support for over 50 languages, with diarization and context biasing. Self-deployment is offered through Mistral sales; no weights are published.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordMistral AI model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Voxtral Mini Transcribe 3, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
Voxtral Mini Transcribe 3 is a proprietary model with a 32K context window. No explicit reasoning mode is documented in this profile.
Released October 20, 2026 as a public preview in the Mistral API as `voxtral-mini-transcribe-3-0`. Mistral reports 4B parameters and support for over 50 languages, with diarization and context biasing. Self-deployment is offered through Mistral sales; no weights are published.
Voxtral Mini Transcribe 3 is a 4B-parameter batch speech-to-text model with diarization and context biasing. Its speech results stay separate from weighted text-model rankings.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 20, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Voxtral Mini Transcribe 3 perform overall in AI benchmarks?
Voxtral Mini Transcribe 3 has published speech or voice results in Voxtral 3 launch evaluation. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does Voxtral Mini Transcribe 3 have full benchmark coverage on BenchLM?
No. Voxtral Mini Transcribe 3's speech or voice results appear in Voxtral 3 launch evaluation, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of Voxtral Mini Transcribe 3?
Voxtral Mini Transcribe 3 has a documented context window of 32K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.