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

Llama 4 Scout×

DeepSeek-R1×

Llama 4 Maverick×

Mistral Large 2×Clear all

	Llama 4 Scout Meta	DeepSeek-R1 DeepSeek	Llama 4 Maverick Meta	Mistral Large 2 Mistral
Vendor	Meta	DeepSeek	Meta	Mistral
Family	Llama	DeepSeek	Llama	Mistral
Release date	2025-04-05	2025-01-20	2025-04-05	2024-07-24
Context window	10,000,000 tokens	128,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	109B	671B	400B	123B
Modality	text, vision	text	text, vision	text
License	Llama 4 Community License	MIT	Llama 4 Community License	Mistral Research License
Source	open weights	open weights	open weights	open weights
Description	—	Reasoning-focused open-weight model.	Mixture-of-experts open-weight model from Meta.	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.
Links	weights →	weights →	weights →	vendor →weights →
Benchmarks
MMLU-Pro	—	—	80.5%	—
HumanEval	—	—	—	89.0%
AIME-25	—	79.8%	—	—
MMMU	—	—	68.5%	—