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×

Llama 4 Scout×

DeepSeek-R1×

Gemini 3 Pro×Clear all

	Grok 4 xAI	Llama 4 Scout Meta	DeepSeek-R1 DeepSeek	Gemini 3 Pro Google
Vendor	xAI	Meta	DeepSeek	Google
Family	Grok	Llama	DeepSeek	Gemini
Release date	2025-07-09	2025-04-05	2025-01-20	2026-04-22
Context window	256,000 tokens	10,000,000 tokens	128,000 tokens	2,000,000 tokens
Parameters	—	109B	671B	—
Modality	text	text, vision	text	text, vision, audio, video
License	proprietary	Llama 4 Community License	MIT	proprietary
Source	proprietary	open weights	open weights	proprietary
Description	—	—	Reasoning-focused open-weight model.	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 →	weights →	vendor →
Benchmarks
MMLU-Pro	82.8%	—	—	87.1%
GPQA-D	87.5%	—	—	88.6%
HumanEval	—	—	—	96.5%
Aider	72.5%	—	—	84.8%
AIME-25	86.1%	—	79.8%	92.8%
LiveCB	65.3%	—	—	76.1%
MMMU	—	—	—	84.3%