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
Not ranked yet
Too few independent or third-party results to rank:
Scientific reasoning, Mathematics, Long context, OCR & documents, Law, Medicine & health, Finance, Multilingual, Instruction following, Writing, Speech & audio.
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· Language
Context
Input price
Weights· Open weights
Reasoning
- Phi-mini-MoEMicrosoft · 23 Jun 2025 · 4.1K context—in / 1M
- Phi-tiny-MoEMicrosoft · 23 Jun 2025 · 4.1K context—in / 1M
- MAI-DS-R1Microsoft · 16 Apr 2025 · 163.8K context—in / 1M
- BitNet b1.58 2B4TMicrosoft · 15 Apr 2025 · 4.1K context—in / 1M
- Phi-4-miniMicrosoft · 26 Feb 2025 · 131.1K context$0.07in / 1M
- Phi-4Microsoft · 12 Dec 2024 · 16.4K context$0.13in / 1M
- Phi-3.5-miniMicrosoft · 20 Aug 2024 · 131.1K context—in / 1M
- Phi-3.5-MoEMicrosoft · 20 Aug 2024 · 131.1K context—in / 1M
- Phi-3-mediumMicrosoft · 21 May 2024 · 131.1K context—in / 1M
- Phi-3-smallMicrosoft · 21 May 2024 · 131.1K context—in / 1M
- Phi-3-miniMicrosoft · 23 Apr 2024 · 131.1K context—in / 1M
- Phi-2Microsoft · 12 Dec 2023 · 2K context—in / 1M
- Orca 2 13BMicrosoft · 20 Nov 2023 · 4.1K context—in / 1M
- Orca 2 7BMicrosoft · 20 Nov 2023 · 4.1K context—in / 1M
- Phi-1.5Microsoft · 11 Sep 2023 · 2K context—in / 1M
- Phi-1Microsoft · 10 Sep 2023 · 2K context—in / 1M