ARK-ASR-3B
As of 1 Nov 2026, ARK-ASR-3B is the RightSignal pick for best open-weight STT.
ARK-ASR-3B heads the Open ASR Leaderboard's public listing at 4.76 mean WER with an RTFx of 490.98, ahead of MOSS-Transcribe-preview-2B on 4.87, MOSS-Transcribe-Diarize on 5.17 and Cohere Transcribe on 5.42, with per-dataset results filed in the repo and dated 23 June 2026.
Launched on 20 October 2026 and still #3 on the Artificial Analysis non-streaming board at 2.1% AA-WER with a median speed factor of 62.2, behind Fun-Realtime-ASR-preview (1.7%) and MAI-Transcribe-2 (2.0%). That index averages only three datasets, so it will not line up with the Open ASR Leaderboard's eight-set mean, where this model does not appear and ARK-ASR-3B holds at 4.76. Artificial Analysis does not count it among its open-weights entries — its best open-weights row is the older Voxtral Small at 2.8% — so despite Mistral's claimed 50+ languages, the licence and weight availability this slot needs are still unverified.
Why it’s the challengercurrent reign
held off
reigns
Why ARK-ASR-3B is the pick
- ARK-ASR-3B heads the Open ASR Leaderboard's public listing at 4.76 mean WER with an RTFx of 490.98, ahead of MOSS-Transcribe-preview-2B on 4.87, MOSS-Transcribe-Diarize on 5.17 and Cohere Transcribe on 5.42, with per-dataset results filed in the repo and dated 23 June 2026.
- The 5.04% on the card is the seven-set average that omits TEDLIUM; add TEDLIUM's 2.79% and you get the board figure.
- It ships Apache-2.0 with 19 languages, but that is not what separates it from MOSS: only the preview-2B is English-only, while MOSS-Transcribe-Diarize is also Apache-2.0 and covers 50+ languages, so ARK's edge there is accuracy rather than licence or reach.
Evidence
The sources behind this title’s record.
- artificialanalysis.ai/speech-to-text
- huggingface.co/spaces/hf-audio/open_asr_leaderboard
- huggingface.co/Audio8/ARK-ASR-3B
- huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B
- arxiv.org/abs/2609.04404
- arxiv.org/abs/2609.04260
- arxiv.org/abs/2609.04225
- huggingface.co/datasets/hf-audio/open-asr-leaderboard
Vendor numbers are treated as claims until independently reproduced — how we judge. Structured benchmark comparisons are on the roadmap.
Caveats & challengers
- NVIDIA's Parakeet-TDT-0.6B-v3 is still the sensible choice where throughput decides the invoice — 25 European languages, automatic language detection and a 6.34% average WER, so you are trading roughly 1.5 WER points for the speed — but note it ships under CC BY 4.0, not Apache-2.0.
- ARK's headline is board-verified rather than card-only: the leaderboard records 4.76 mean WER at RTFx 490.98, including TEDLIUM at 2.79%.
- Do budget for less throughput headroom than that suggests, though: AutoArk's own rerun of the seven public splits on 8x RTX 4090, scored with the leaderboard scorer, lands at 5.13% WER and an overall RTFx of 197.
Launched on 20 October 2026 and still #3 on the Artificial Analysis non-streaming board at 2.1% AA-WER with a median speed factor of 62.2, behind Fun-Realtime-ASR-preview (1.7%) and MAI-Transcribe-2 (2.0%). That index averages only three datasets, so it will not line up with the Open ASR Leaderboard's eight-set mean, where this model does not appear and ARK-ASR-3B holds at 4.76. Artificial Analysis does not count it among its open-weights entries — its best open-weights row is the older Voxtral Small at 2.8% — so despite Mistral's claimed 50+ languages, the licence and weight availability this slot needs are still unverified.
Microsoft has now filled in the gaps: the 7B card ships under MIT, and the streaming technical report (arXiv 2609.02812) quotes a real-time factor at or below 0.104 on an A100, with ten languages supported rather than the four originally tagged. The accuracy numbers are still the authors' own — it does not appear on the Open ASR Leaderboard, which ARK-ASR-3B continues to head at 4.76 mean WER. Worth a look if you need streaming speaker-attributed transcription, but you cannot yet compare it like-for-like on WER.
Both still appear on the Artificial Analysis non-streaming speech-to-text board, but neither is near the top as of 1 November 2026: Qwen3.5 Omni Flash sits at 13.5% AA-WER and Qwen3.5 Omni Plus at 3.5%, against Fun-Realtime-ASR-preview at 1.7%, MAI-Transcribe-2 at 2.0% and Voxtral Small Transcribe 3 at 2.1%. That board ranks by an AA-WER index built from three datasets (AA-AgentTalk, VoxPopuli-Cleaned-AA, Earnings22-Cleaned-AA), so it is not comparable with the Open ASR Leaderboard's eight-set mean, and it lists no licence or weight availability for either variant. Neither appears on the Open ASR Leaderboard, which ARK-ASR-3B still heads at 4.76 mean WER.
At a glance
- Title
- Best open-weight STT
- Licence
- Apache-2.0
- Pick since
- 22 Jun 2026
- Last reviewed
- 1 Nov 2026
- Title holders to date
- 7
- Official page
- huggingface.co/Audio8/ARK-ASR-3B
Title history
Every change, on the record.
ARK-ASR-3B heads the Open ASR Leaderboard's public listing at 4.76 mean WER with an RTFx of 490.98, ahead of MOSS-Transcribe-preview-2B on 4.87, MOSS-Transcribe-Diarize on 5.17 and Cohere Transcribe on 5.42, with per-dataset results filed in the repo and dated 23 June 2026.
132 daysas pick
IBM finally pushed past the long-standing Canary Qwen number at 5.33% WER under Apache-2.0 — and 300k downloads say people actually switc…
54 daysas pick
Bolting an LLM decoder onto the Canary encoder hit 5.63% WER and gave transcription plus summarisation in one pass; nothing open beat it …
286 daysas pick
Topped the leaderboard at 600M parameters with absurd throughput — the obvious pick for bulk transcription rather than benchmark chasing.
77 daysas pick
Took the top of the Open ASR Leaderboard off Whisper at a third of the size — and NVIDIA held that spot for over a year.
449 daysas pick
The DevDay refresh cut errors meaningfully over v2 on most languages and became the drop-in replacement overnight.
92 daysas pick
as pick