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

GPT-4.1×

Grok 4×

DeepSeek-V4-Pro×

Gemini 3 Pro×Clear all

	GPT-4.1 OpenAI	Grok 4 xAI	DeepSeek-V4-Pro DeepSeek	Gemini 3 Pro Google
Vendor	OpenAI	xAI	DeepSeek	Google
Family	GPT	Grok	DeepSeek	Gemini
Release date	2025-04-14	2025-07-09	2026-04-22	2026-04-22
Context window	1,000,000 tokens	256,000 tokens	1,000,000 tokens	2,000,000 tokens
Parameters	—	—	1.6T (49B active)	—
Modality	text, vision	text	text	text, vision, audio, video
License	proprietary	proprietary	MIT	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	—	—	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.	Google DeepMind's flagship multimodal model. Best-in-class for multimodal understanding and agentic / vibe coding workflows. A "Deep Think" reasoning mode is available to AI Ultra subscribers.
Links		vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	—	82.8%	84.2%	87.1%
GPQA-D	—	87.5%	82.4%	88.6%
HumanEval	—	—	95.1%	96.5%
Aider	—	72.5%	80.1%	84.8%
AIME-25	—	86.1%	88.6%	92.8%
LiveCB	—	65.3%	72.4%	76.1%
MMMU	—	—	—	84.3%