ARTIFICIAL ANALYSIS
Word Error Rate.
Artificial Analysis non-streaming AA-WER index for speech-to-text models. Lower is better. Snapshot 29 Oct 2026.
Lower word error rate is better. AA-WER v2 is the non-streaming index. Speed factor is median input-audio seconds transcribed per second. Price is USD per 1,000 minutes.
Artificial Analysis speech-to-text leaderboard ↗Snapshot 29 Oct 2026. Rankings are Artificial Analysis’s, not scores from this newsroom.
| Rank | Model | Provider | Whisper | Word error rate | Median speed factor | USD / 1,000 min |
|---|---|---|---|---|---|---|
| 1 | Fun-Realtime-ASR-preview, Alibaba | Alibaba Cloud | — | 1.7% | 20.6 | $2.82 |
| 2 | MAI-Transcribe-2 | Microsoft AI | — | 2.0% | 310.4 | $1.67 |
| 3 | Voxtral Small Transcribe 3 | Mistral | — | 2.1% | 64.2 | $4.00 |
| 4 | Scribe v2 | ElevenLabs | — | 2.2% | 73.4 | $3.67 |
| 5 | Voxtral Mini Transcribe 3 | Mistral | — | 2.2% | 76.6 | $3.50 |
| 6 | Grok Voice Transcribe 2.0 | SpaceXAI | — | 2.3% | 182.9 | $1.67 |
| 7 | MAI-Transcribe-1.5 | Microsoft AI | — | 2.4% | 81.3 | $6.00 |
| 8 | StepAudio 3 ASR | StepFun | — | 2.5% | 64.0 | $6.67 |
| 9 | Gemini 3.5 Transcribe | — | 2.6% | 89.0 | $5.00 | |
| 10 | Zoom Scribe V2 Pro | Zoom | — | 2.8% | 124.0 | $3.33 |
| 11 | Voxtral Small | Mistral | — | 2.8% | 57.3 | $4.00 |
| 12 | Gemini 3.1 Pro Preview (High) | — | 2.8% | 8.1 | $18.15 | |
| 13 | Gemini 2.5 Pro | — | 2.9% | 9.7 | $11.39 | |
| 14 | Gemini 3 Flash (High) | — | 2.9% | 21.0 | $13.70 | |
| 15 | Universal-3.5 Pro | AssemblyAI | — | 3.0% | 104.2 | $3.50 |
| 16 | Universal-3 Pro | AssemblyAI | — | 3.1% | 100.0 | $3.50 |
| 17 | Solaria-3 | Gladia | — | 3.2% | 92.9 | $10.16 |
| 18 | GPT Transcribe | OpenAI | — | 3.3% | 46.1 | $4.50 |
| 19 | Smallest AI Pulse | Smallest.ai | — | 3.3% | 254.8 | $5.00 |
| 20 | Resonant-1 | Reson8 | — | 3.4% | 337.1 | $3.60 |
| 21 | Smallest AI Pulse Pro | Smallest.ai | — | 3.4% | 297.6 | $4.00 |
| 22 | Gemini 3.1 Flash-Lite Preview (Minimal) | — | 3.4% | 89.9 | $5.83 | |
| 23 | Qwen3.5 Omni Plus | Alibaba Cloud | — | 3.5% | 149.1 | $0.00 |
| 24 | Gemini 3.1 Pro Preview (Low) | — | 3.6% | 8.5 | $7.72 | |
| 25 | Voxtral Mini Transcribe 2 | Mistral | — | 3.6% | 86.7 | $3.00 |
| 26 | Soniox v5 Async | Soniox | — | 3.8% | 41.0 | $1.66 |
| 27 | Universal | AssemblyAI | — | 3.8% | 102.8 | $2.50 |
| 28 | Voxtral Mini, Deepinfra | DeepInfra | — | 3.8% | 47.1 | $1.00 |
| 29 | Inworld STT 1 | Inworld | — | 3.9% | 142.0 | $2.50 |
| 30 | GPT-4o Transcribe | OpenAI | — | 4.0% | 37.9 | $6.00 |
| 31 | Enhanced | Speechmatics | — | 4.0% | 52.3 | $12.50 |
| 32 | Large v2 | OpenAI | large-v2 | 4.1% | 28.5 | $6.00 |
| 33 | Solaria-1 | Gladia | — | 4.1% | 92.2 | $10.17 |
| 34 | Whisper (L, v3), fal.ai | fal.ai | large-v3 | 4.1% | 91.5 | $1.15 |
| 35 | Amazon Transcribe | Amazon Bedrock | — | 4.1% | 34.9 | $6.00 |
| 36 | Modulate STT Batch English VFast | Modulate | — | 4.2% | 55.5 | $0.42 |
| 37 | Canary Qwen 2.5B, Replicate | Replicate | — | 4.3% | 8.4 | $0.74 |
| 38 | Chirp 3 | — | 4.3% | 29.6 | $16.00 | |
| 39 | GPT-4o Mini Transcribe | OpenAI | — | 4.5% | 45.4 | $3.00 |
| 40 | Whisper Large v3, together.ai | Together AI | large-v3 | 4.5% | 294.4 | $1.50 |
| 41 | Parakeet TDT 0.6B V3, Togetherai | Together AI | — | 4.5% | 687.0 | $1.50 |
| 42 | Cohere Transcribe 03-2026 | Cohere | — | 4.6% | 66.3 | $0.00 |
| 43 | Whisper (L, v3, Turbo), Groq | Groq | v3 Turbo | 4.6% | 276.8 | $0.67 |
| 44 | StepAudio 2.5 ASR | StepFun | — | 4.7% | 115.3 | $0.37 |
| 45 | Wizper (L, v3), fal.ai | fal.ai | large-v3 | 4.7% | 152.3 | $0.50 |
| 46 | Nova-3, Telnyx | Telnyx | — | 4.8% | 500.9 | $7.40 |
| 47 | Nova 2 Pro | Amazon Bedrock | — | 4.9% | 23.4 | $3.10 |
| 48 | Melia | Speechmatics | — | 4.9% | 176.8 | $4.00 |
| 49 | Nova-2, Telnyx | Telnyx | — | 5.1% | 457.5 | $7.40 |
| 50 | Standard | Speechmatics | — | 5.1% | 87.8 | $7.50 |
| 51 | Gemini 2.5 Flash | — | 5.1% | 66.7 | $6.66 | |
| 52 | Gemini 2.5 Flash Lite | — | 5.2% | 74.6 | $6.56 | |
| 53 | Nova-3 | Deepgram | — | 5.2% | 623.2 | $4.30 |
| 54 | Parakeet RNNT 1.1B, Replicate | Replicate | — | 5.4% | 6.3 | $1.91 |
| 55 | Whisper Large v3 Turbo, Telnyx | Telnyx | — | 5.5% | 37.0 | $15.00 |
| 56 | Incredibly Fast, Replicate | Replicate | large-v3 | 5.7% | 55.0 | $1.49 |
| 57 | Rev AI | Rev AI | — | 5.9% | 13.1 | $3.33 |
| 58 | Parakeet TDT 0.6B V2 | NVIDIA | — | 6.4% | 97.4 | $0.00 |
| 59 | Gradium Speech-to-Text | Gradium | — | 6.8% | 2.3 | $13.00 |
| 60 | Whisper (L, v3), Replicate | Replicate | large-v3 | 10.1% | 2.9 | $4.23 |
| 61 | Qwen3.5 Omni Flash | Alibaba Cloud | — | 13.5% | 70.9 | $0.00 |
| 62 | Chirp | — | 31.2% | 14.3 | $16.00 |