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

Grok 4×

GPT-5.5×

DeepSeek-V4-Pro×

GPT-5×Clear all

	Grok 4 xAI	GPT-5.5 OpenAI	DeepSeek-V4-Pro DeepSeek	GPT-5 OpenAI
Vendor	xAI	OpenAI	DeepSeek	OpenAI
Family	Grok	GPT	DeepSeek	GPT
Release date	2025-07-09	2026-04-23	2026-04-22	2025-08-07
Context window	256,000 tokens	400,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	—	—	1.6T (49B active)	—
Modality	text	text, vision, audio	text	text, vision, audio
License	proprietary	proprietary	MIT	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	—	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.	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.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.
Links	vendor →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	82.8%	87.6%	84.2%	85.1%
GPQA-D	87.5%	89.4%	82.4%	87.3%
HumanEval	—	96.8%	95.1%	95.2%
Aider	72.5%	89.7%	80.1%	85.4%
AIME-25	86.1%	94.2%	88.6%	91.0%
LiveCB	65.3%	78.9%	72.4%	74.5%
MMMU	—	78.4%	—	74.1%