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 Maverick×

Grok 4×

DeepSeek-R1×

DeepSeek-V4-Pro×Clear all

	Llama 4 Maverick Meta	Grok 4 xAI	DeepSeek-R1 DeepSeek	DeepSeek-V4-Pro DeepSeek
Vendor	Meta	xAI	DeepSeek	DeepSeek
Family	Llama	Grok	DeepSeek	DeepSeek
Release date	2025-04-05	2025-07-09	2025-01-20	2026-04-22
Context window	1,000,000 tokens	256,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	400B	—	671B	1.6T (49B active)
Modality	text, vision	text	text	text
License	Llama 4 Community License	proprietary	MIT	MIT
Source	open weights	proprietary	open weights	open weights
Description	Mixture-of-experts open-weight model from Meta.	—	Reasoning-focused open-weight model.	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.
Links	weights →	vendor →	weights →	weights →
Benchmarks
MMLU-Pro	80.5%	82.8%	—	84.2%
GPQA-D	—	87.5%	—	82.4%
HumanEval	—	—	—	95.1%
Aider	—	72.5%	—	80.1%
AIME-25	—	86.1%	79.8%	88.6%
LiveCB	—	65.3%	—	72.4%
MMMU	68.5%	—	—	—