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×

Gemini 3.5×

DeepSeek-R1×

Llama 4 Maverick×Clear all

	Grok 4 xAI	Gemini 3.5 Google	DeepSeek-R1 DeepSeek	Llama 4 Maverick Meta
Vendor	xAI	Google	DeepSeek	Meta
Family	Grok	Gemini	DeepSeek	Llama
Release date	2025-07-09	2026-05-20	2025-01-20	2025-04-05
Context window	256,000 tokens	2,000,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	—	—	671B	400B
Modality	text	text, vision, audio, video	text	text, vision
License	proprietary	proprietary	MIT	Llama 4 Community License
Source	proprietary	proprietary	open weights	open weights
Description	—	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Reasoning-focused open-weight model.	Mixture-of-experts open-weight model from Meta.
Links	vendor →	vendor →	weights →	weights →
Benchmarks
MMLU-Pro	82.8%	88.9%	—	80.5%
GPQA-D	87.5%	91.2%	—	—
Aider	72.5%	—	—	—
AIME-25	86.1%	96.1%	79.8%	—
LiveCB	65.3%	—	—	—
MMMU	—	86.0%	—	68.5%