Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Comparing agents instead? Switch to agent compare →

Selected

DeepSeek-R1×

Mistral Large 2×

Llama 4 Scout×

DeepSeek-V3.1×Clear all

	DeepSeek-R1 DeepSeek	Mistral Large 2 Mistral	Llama 4 Scout Meta	DeepSeek-V3.1 DeepSeek
Vendor	DeepSeek	Mistral	Meta	DeepSeek
Family	DeepSeek	Mistral	Llama	DeepSeek
Release date	2025-01-20	2024-07-24	2025-04-05	2025-08-21
Context window	128,000 tokens	128,000 tokens	10,000,000 tokens	128,000 tokens
Parameters	671B	123B	109B	671B
Modality	text	text	text, vision	text
License	MIT	Mistral Research License	Llama 4 Community License	MIT
Source	open weights	open weights	open weights	open weights
Description	Reasoning-focused open-weight model.	Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line.	—	Large MoE open-weight model. Predecessor to DeepSeek-V4.
Links	weights →	vendor →weights →	weights →	weights →
Benchmarks
HumanEval	—	89.0%	—	—
AIME-25	79.8%	—	—	—