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

14 modelsMaker: Microsoft Context: 128K and up Clear all

Models
Model	Maker	Kind	Released	Context	Input $/1M	Output $/1M
MAI-Thinking-1MAI	Microsoft	Language	2 Jun 2026	256K	—	—
Fara1.5-9BFara · Open weights	Microsoft	Vision-language	12 May 2026	262.1K	—	—
Phi-4-mini-reasoningPhi Reasoning · Open weights	Microsoft	Reasoning-only	30 Apr 2025	131.1K	$0.07	$0.30
MAI-DS-R1MAI · Legacy · Open weights	Microsoft	Language	16 Apr 2025	163.8K	—	—
Phi-4-miniPhi · Open weights	Microsoft	Language	26 Feb 2025	131.1K	$0.07	$0.30
Phi-4-multimodalPhi Vision / Multimodal · Open weights	Microsoft	Vision-language	26 Feb 2025	131.1K	$0.08	$0.32
Phi-3.5-miniPhi · Legacy · Open weights	Microsoft	Language	20 Aug 2024	131.1K	—	—
Phi-3.5-MoEPhi · Legacy · Open weights	Microsoft	Language	20 Aug 2024	131.1K	—	—
Phi-3.5-visionPhi Vision / Multimodal · Legacy · Open weights	Microsoft	Vision-language	20 Aug 2024	131.1K	—	—
Phi-3-mediumPhi · Legacy · Open weights	Microsoft	Language	21 May 2024	131.1K	—	—
Phi-3-smallPhi · Legacy · Open weights	Microsoft	Language	21 May 2024	131.1K	—	—
Phi-3-visionPhi Vision / Multimodal · Legacy · Open weights	Microsoft	Vision-language	21 May 2024	131.1K	—	—
Phi-3-miniPhi · Legacy · Open weights	Microsoft	Language	23 Apr 2024	131.1K	—	—
Fara-7BFara · Legacy · Open weights	Microsoft	Vision-language	—	128K	—	—