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×

Gemini 3.5×

Llama 4 Maverick×Clear all

	Grok 4 xAI	DeepSeek-V4-Pro DeepSeek	Gemini 3.5 Google	Llama 4 Maverick Meta
Vendor	xAI	DeepSeek	Google	Meta
Family	Grok	DeepSeek	Gemini	Llama
Release date	2025-07-09	2026-04-22	2026-05-20	2025-04-05
Context window	256,000 tokens	1,000,000 tokens	2,000,000 tokens	1,000,000 tokens
Parameters	—	1.6T (49B active)	—	400B
Modality	text	text	text, vision, audio, video	text, vision
License	proprietary	MIT	proprietary	Llama 4 Community License
Source	proprietary	open weights	proprietary	open weights
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 next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Mixture-of-experts open-weight model from Meta.
Links	vendor →	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	82.8%	84.2%	88.9%	80.5%
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	—	—	86.0%	68.5%