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×

DeepSeek-V4-Pro×

Llama 4 Maverick×

Gemini 3.5×Clear all

	Grok 4 xAI	DeepSeek-V4-Pro DeepSeek	Llama 4 Maverick Meta	Gemini 3.5 Google
Vendor	xAI	DeepSeek	Meta	Google
Family	Grok	DeepSeek	Llama	Gemini
Release date	2025-07-09	2026-04-22	2025-04-05	2026-05-20
Context window	256,000 tokens	1,000,000 tokens	1,000,000 tokens	2,000,000 tokens
Parameters	—	1.6T (49B active)	400B	—
Modality	text	text	text, vision	text, vision, audio, video
License	proprietary	MIT	Llama 4 Community License	proprietary
Source	proprietary	open weights	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.	Mixture-of-experts open-weight model from Meta.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.
Links	vendor →	weights →	weights →	vendor →
Benchmarks
MMLU-Pro	82.8%	84.2%	80.5%	88.9%
GPQA-D	87.5%	82.4%	—	91.2%
HumanEval	—	95.1%	—	—
Aider	72.5%	80.1%	—	—
AIME-25	86.1%	88.6%	—	96.1%
LiveCB	65.3%	72.4%	—	—
MMMU	—	—	68.5%	86.0%