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-V3.1×

Grok 4×

Llama 4 Maverick×

GPT-5.5×Clear all

	DeepSeek-V3.1 DeepSeek	Grok 4 xAI	Llama 4 Maverick Meta	GPT-5.5 OpenAI
Vendor	DeepSeek	xAI	Meta	OpenAI
Family	DeepSeek	Grok	Llama	GPT
Release date	2025-08-21	2025-07-09	2025-04-05	2026-04-23
Context window	128,000 tokens	256,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	671B	—	400B	—
Modality	text	text	text, vision	text, vision, audio
License	MIT	proprietary	Llama 4 Community License	proprietary
Source	open weights	proprietary	open weights	proprietary
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	—	Mixture-of-experts open-weight model from Meta.	OpenAI's smartest and most intuitive model — successor to GPT-5, with major coding, research, and document workflow gains. GPT-5.5 Pro variant also available for heavier reasoning.
Links	weights →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	—	82.8%	80.5%	87.6%
GPQA-D	—	87.5%	—	89.4%
HumanEval	—	—	—	96.8%
Aider	—	72.5%	—	89.7%
AIME-25	—	86.1%	—	94.2%
LiveCB	—	65.3%	—	78.9%
MMMU	—	—	68.5%	78.4%