Model catalog
This speech-to-text leaderboard compares the available benchmark ranking, score status, per-minute pricing and streaming capabilities without combining unlike evaluations.
Data as of 2026-09-08
Browse the speech-to-text leaderboard ranking alongside the full catalog. Models without enough comparable benchmark evidence remain unscored.
Model | LLMBoard score | Input -> output | Native price | Provider | Context | Released |
|---|
| ModelAUARK-ASR-3BAudio8 | LLMBoard score70.77 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOTMOSS-Transcribe-preview-2BOpenmoss Team | LLMBoard score70.07 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelOTMOSS-Transcribe-DiarizeOpenmoss Team | LLMBoard score69.36 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCOcohere-transcribe-03-2026Coherelabs | LLMBoard score68.66 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAUARK-ASR-0.6BAudio8 | LLMBoard score67.96 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOZipformer-cr-ctc-transducer-XL-290MSoundsgoodai | LLMBoard score67.25 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAC | LLMBoard score66.55 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMI | LLMBoard score65.84 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score64.43 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelKYstt-2.6b-enKyutai | LLMBoard score63.73 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAC | LLMBoard score63.02 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score62.32 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMAmoonshine-streaming-mediumMoonshine Ai | LLMBoard score61.61 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelSOZipformer-transducer-XL-290MSoundsgoodai | LLMBoard score60.91 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score60.21 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAUAudio8-ASR-0.1BAudio8 | LLMBoard score59.15 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelZA | LLMBoard score59.15 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelMIVoxtral-Mini-3B-2507Mistralai | LLMBoard score58.10 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score57.39 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score55.99 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelDWdistil-large-v3.5Distil Whisper | LLMBoard score55.28 | Input -> outputunspecified -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAM | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelNV | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelCO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelAL | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
| ModelGO | LLMBoard score55.09 | Input -> outputaudio -> text | Native priceN/A | ProviderN/A | ContextN/A | ReleasedN/A |
This leaderboard uses evaluation and benchmark evidence only for scores. Price, context and model specifications remain separate from the ranking.
Use price as context for the leaderboard, not as part of its benchmark ranking. Each listing keeps its original unit.
Compare input and output support alongside the leaderboard; modality support does not change the benchmark ranking.
114 models currently have a domain-specific LLMBoard score. The leaderboard ranking uses matched benchmark evidence, while coverage and provisional status identify incomplete evidence.
Whisper Large V3 Turbo has the lowest current native price at $0.0007 / minute via Groq.
ARK-ASR-3B leads the available LLMBoard scores at 70.77.
0 of 125 catalog models have more than one listed input modality.
120 catalog models currently have no positive native-unit price listing.
Prices retain the unit returned by the catalog, such as per image, per second, per minute or per million characters. They are never shown as token prices.
Some models do not have a current price listing in their native billing unit.