Updated daily at 05:00 UTC
Models
AI models
1521 current models, newest first. Each links to its benchmark results, with who ran them.
Best by specialty
Independent and third-party results only · method category-2026-09-29.1
All current models
Best for
- Knowledge & reasoning
- Scientific reasoning
- Mathematics
- Coding & software engineering
- Agentic tool use
- Computer & browser use
- Professional knowledge work
- Long context
- Vision & multimodal understanding
- OCR & documents
- Law
- Medicine & health
- Finance
- Multilingual
- Factuality & hallucination
- Instruction following
- Writing
- Speech & audio
- Human preference
Kind· Speech-to-text
Context
Input price
Weights
Reasoning
- Scribe v2 MedicalElevenLabs · 11 Sep 2026 · — context—in / 1M
- MAI-Transcribe-2Microsoft · 3 Sep 2026 · — context—in / 1M
- VibeVoice-ASR-Streaming (1.5B / 7B)Microsoft · 2 Sep 2026 · — context—in / 1M
- Grok Voice Transcribe 2.0SpaceXAI (xAI) · Sep 2026 · — context—in / 1M
- Gemini 3.5 TranscribeGoogle DeepMind · 26 Aug 2026 · — context$2.00in / 1M
- Gemini 3.5 Transcribe LiveGoogle DeepMind · 26 Aug 2026 · — context$3.50in / 1M
- Granite Speech 5.0 470M TurboCTCIBM · 4 Aug 2026 · — context—in / 1M
- Qwen-Audio-3.0-ASRAlibaba Group · 30 Jul 2026 · — context—in / 1M
- GPT Live TranscribeOpenAI · 28 Jul 2026 · — context—in / 1M
- GPT TranscribeOpenAI · 28 Jul 2026 · — context—in / 1M
- Cohere Transcribe ArabicCohere · Jul 2026 · — context—in / 1M
- MAI-Transcribe-1.5Microsoft · 2 Jun 2026 · — context—in / 1M
- Nemotron 3.5 ASR Streaming 0.6BNVIDIA · 15 May 2026 · — context—in / 1M
- GPT-Realtime-WhisperOpenAI · 7 May 2026 · 16K context—in / 1M
- Granite Speech 4.1 2B (and 2B-plus, 2B-NAR)IBM · 16 Apr 2026 · — context—in / 1M
- MAI-Transcribe-1Microsoft · 2 Apr 2026 · — context—in / 1M
- Grok Voice Transcribe 1.0SpaceXAI (xAI) · Apr 2026 · — context—in / 1M
- StepAudio 2.5 ASRStepFun · Apr 2026 · — context—in / 1M
- Cohere TranscribeCohere · 24 Mar 2026 · — context—in / 1M
- Granite 4.0 1B SpeechIBM · 27 Feb 2026 · — context—in / 1M
- Voxtral Mini Transcribe 2Mistral AI · 4 Feb 2026 · — context—in / 1M
- Voxtral Mini Transcribe RealtimeMistral AI · 4 Feb 2026 · — context—in / 1M
- Qwen3-ASR (open)Alibaba Group · 29 Jan 2026 · — context—in / 1M
- VibeVoice-ASRMicrosoft · 21 Jan 2026 · — context—in / 1M
- Nemotron Speech Streaming EN 0.6BNVIDIA · 17 Dec 2025 · — context—in / 1M
- Fun-ASR-Nano-2512Alibaba Group · 15 Dec 2025 · — context—in / 1M
- GLM-ASR-2512Z.ai (Zhipu AI) · 10 Dec 2025 · — context—in / 1M
- Deepgram Flux (English, Multilingual)Deepgram · Oct 2025 · — context—in / 1M
- Qwen3-Omni-30B-A3B-CaptionerAlibaba Group · 22 Sep 2025 · — context$3.81in / 1M
- Qwen3-ASR-FlashAlibaba Group · 8 Sep 2025 · — context—in / 1M
- Chirp 3Google · 29 Aug 2025 · — context—in / 1M
- Fun-ASRAlibaba Group · 25 Aug 2025 · — context—in / 1M
- Canary 1B v2NVIDIA · 4 Aug 2025 · — context—in / 1M
- Parakeet TDT 0.6B v3NVIDIA · 4 Aug 2025 · — context—in / 1M
- OLMoASRAllen Institute for AI (Ai2) · Aug 2025 · — context—in / 1M
- Canary-Qwen 2.5BNVIDIA · 26 Jun 2025 · — context—in / 1M
- Parakeet TDT 0.6B v2NVIDIA · 15 Apr 2025 · — context—in / 1M
- Granite Speech 3.3 (2B, 8B)IBM · Apr 2025 · — context—in / 1M
- Granite Speech 3.2 8BIBM · 26 Mar 2025 · — context—in / 1M
- GPT-4o mini TranscribeOpenAI · 20 Mar 2025 · 16K context$1.25in / 1M
- GPT-4o TranscribeOpenAI · 20 Mar 2025 · 16K context$2.50in / 1M
- Canary 1B FlashNVIDIA · 7 Mar 2025 · — context—in / 1M
- Deepgram Nova-3Deepgram · Feb 2025 · — context—in / 1M
- Whisper large-v3-turboOpenAI · 30 Sep 2024 · — context—in / 1M
- Qwen2-Audio-7B-InstructAlibaba Group · 9 Aug 2024 · 8.2K context—in / 1M
- SenseVoice-SmallAlibaba Group · Jul 2024 · — context—in / 1M
- Canary 1BNVIDIA · 7 Feb 2024 · — context—in / 1M
- Parakeet TDT 1.1BNVIDIA · 25 Jan 2024 · — context—in / 1M
- Parakeet CTC / RNNT 1.1BNVIDIA · 28 Dec 2023 · — context—in / 1M
- Qwen-Audio-ChatAlibaba Group · 30 Nov 2023 · 2K context—in / 1M