Unranked
AS
Best
AssemblyAI
N/A LLMBoard
OpenAI model product
State-of-the-art multilingual transcription with high accuracy.
Updated Aug 12, 2026. Default version: Whisper Large V3
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
No version of this model currently has enough benchmark coverage for a score.
Benchmark scores for the scored version.
No benchmark result is linked to the scored version.
Preference and agent-evaluation results for the default version.
The default version does not have a matching Arena result yet.
Provider-specific output speed and catalog latency for Whisper Large V3. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Prices are shown in the model's native media unit and resolution tier.
| Groq | whisper-large-v3 | global | $0.0018 / minute | minute | N/A |
Media catalog prices are not converted into token input or output prices.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Whisper Large V3 | N/A | N/A | N/A | N/A | N/A | No | Unspecified |
Key information about Whisper Large and its available data.
State-of-the-art multilingual transcription with high accuracy. 3% WER, 189x real-time speed. Served by Groq.
Data as of 2026-08-11.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Whisper Large.
A release date is not available for the default version.
Whisper Large's current catalog price is $0.0018 / minute.
Whisper Large was created by OpenAI.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
1 provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.