# Scribe v3 Benchmark Scores & Performance

> Scribe v3 has ElevenLabs launch evaluation results. Voice evidence is display-only and does not produce a text-model score.

Canonical page: https://benchlm.ai/models/scribe-v3

Last updated: November 11, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | ElevenLabs |
| Source Type | Proprietary |
| Reasoning Type | Non-Reasoning |
| Context Window | N/A |
| Official model card | [ElevenLabs model card](https://elevenlabs.io/blog/scribe-v3) |
| Overall Score | Not scored (voice evidence only) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Scribe v3
- Variant: base
- Benchmarks covered: 0 of 815
- Coverage note: Speech and voice results appear below; no weighted text-model benchmark rows are stored.

## Speech and voice evidence

[Scribe v3 launch evaluation](/voice-benchmarks/scribe-v3-launch-evaluation)

ElevenLabs ran every result itself, on an internal version of FLEURS and on its own unreleased dataset, so nothing here is independently reproducible yet. Each FLEURS language is scored on its own and then averaged, which ElevenLabs notes gives higher numbers than pooling clips, so these WERs are not comparable with pooled results elsewhere. The comparisons against other providers use only the languages both models support. The realtime diarization figure aligns each transcript to the reference first and is not comparable with the batch diarization figures. The launch post reports Scribe v3 Live on 102 FLEURS languages; the documentation reports 73. Semantic WER counts an error only when the meaning changes. These transcription results stay separate from BenchLM’s weighted text-model ranking.

| Metric | Result |
| --- | --- |
| FLEURS WER, 102-language mean | 12.38% |
| FLEURS WER, Scribe v2 | 16.94% |
| FLEURS semantic WER, 102-language mean | 4.4% |
| Diarization error rate, internal 16-language set | 5.6% |
| Diarization error rate, 3+ speakers | 8.0% |
| Price | $0.20 per hour |

ElevenLabs launch post and model documentation, read November 11, 2026. Provider-run on an internal copy of FLEURS (October 23–29, 2026) and an unreleased internal meeting and call set (October 26 and November 3, 2026). Each language is scored on its own before averaging. Lower is better. Voice results are display-only.

- [Evaluation source](https://elevenlabs.io/blog/scribe-v3)

### Independent test: [DAI-ASR-I18N](/voice-benchmarks/dai-asr-i18n)

Independent test by David AI: real two-person conversations in 21 languages, version 1.4 of 2026-11-10. Places follow David AI's average rank across languages; error rates are lower-is-better.

| Metric | Result |
| --- | --- |
| Transcription place | #2 of 20 |
| Mean error rate | 14.02% |
| Languages covered | 21 of 21 |
| Diarization place | #4 of 17 |
| Diarization error rate | 23.39% |

Released November 10, 2026 in the ElevenLabs Speech to Text API (POST /v1/speech-to-text) as scribe_v3, and the default in the ElevenLabs app. ElevenLabs lists 90+ languages in its model table and reports results on 102 FLEURS languages. It keeps the Scribe v2 feature set (word timestamps, speaker diarization, audio tagging) and adds inferred language hints, digits-or-words number output, keyterm prompting of up to 1,000 terms, and plain-English formatting rules. Upgrading from Scribe v2 is a model ID change; Scribe v2 remains available. US by default, with isolated EU, India and Singapore environments, Zero Retention Mode, and HIPAA eligibility under a BAA for enterprise customers.

## Other ElevenLabs Models

- [Scribe v3 Live](/models/scribe-v3-live) - Score: not computed
- [ElevenLabs Eleven v4](/models/elevenlabs-eleven-v4) - Score: not computed
- [ElevenLabs Eleven v4 Turbo](/models/elevenlabs-eleven-v4-turbo) - Score: not computed
- [ElevenLabs Eleven v3 Conversational](/models/elevenlabs-eleven-v3-conversational) - Score: not computed
- [ElevenLabs Eleven v3](/models/elevenlabs-eleven-v3) - Score: not computed
- [Eleven Realtime v1 Max](/models/eleven-realtime-v1-max) - Score: not computed
- [Eleven Realtime v1 Mini](/models/eleven-realtime-v1-mini) - Score: not computed
- [Scribe v2.2 Realtime](/models/scribe-v2-2-realtime) - Score: not computed