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

Gemini Omni×

DeepSeek-V4-Pro×

Grok 4×

Gemini 3 Pro×Clear all

	Gemini Omni Google	DeepSeek-V4-Pro DeepSeek	Grok 4 xAI	Gemini 3 Pro Google
Vendor	Google	DeepSeek	xAI	Google
Family	Gemini	DeepSeek	Grok	Gemini
Release date	2026-05-20	2026-04-22	2025-07-09	2026-04-22
Context window	1,000,000 tokens	1,000,000 tokens	256,000 tokens	2,000,000 tokens
Parameters	—	1.6T (49B active)	—	—
Modality	text, vision, audio, video	text	text	text, vision, audio, video
License	proprietary	MIT	proprietary	proprietary
Source	proprietary	open weights	proprietary	proprietary
Description	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	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 →	vendor →
Benchmarks
MMLU-Pro	—	84.2%	82.8%	87.1%
GPQA-D	—	82.4%	87.5%	88.6%
HumanEval	—	95.1%	—	96.5%
Aider	—	80.1%	72.5%	84.8%
AIME-25	—	88.6%	86.1%	92.8%
LiveCB	—	72.4%	65.3%	76.1%
MMMU	82.5%	—	—	84.3%