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-speech
Context· 128K and up
Input price
Weights· Proprietary
Reasoning
- Gemini 3.8 LiveGoogle DeepMind · 15 Sep 2026 · 131.1K context$0.75in / 1M
- Gemini 3.8 Live Extended ThinkingGoogle DeepMind · 15 Sep 2026 · 131.1K context$0.75in / 1M
- GPT-Realtime-2.1OpenAI · 6 Jul 2026 · 128K context$4.00in / 1M
- GPT-Realtime-2.1 miniOpenAI · 6 Jul 2026 · 128K context$0.60in / 1M
- Gemini 3.5 Live TranslateGoogle DeepMind · Jun 2026 · 131.1K context$3.50in / 1M
- GPT-Realtime-2OpenAI · 7 May 2026 · 128K context$4.00in / 1M
- Gemini 3.1 Flash LiveGoogle DeepMind · 26 Mar 2026 · 131.1K context$0.75in / 1M
- GPT Audio 1.5OpenAI · 23 Feb 2026 · 128K context$2.50in / 1M
- GPT Audio miniOpenAI · 6 Oct 2025 · 128K context$0.60in / 1M
- GPT AudioOpenAI · 28 Aug 2025 · 128K context$2.50in / 1M
- Gemini 2.5 Flash Live (Native Audio)Google DeepMind · 20 May 2025 · 131.1K context$0.50in / 1M