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

Llama 4 Maverick×

Gemini 3 Pro×

Gemini Omni×

Gemini 3.5×Clear all

	Llama 4 Maverick Meta	Gemini 3 Pro Google	Gemini Omni Google	Gemini 3.5 Google
Vendor	Meta	Google	Google	Google
Family	Llama	Gemini	Gemini	Gemini
Release date	2025-04-05	2026-04-22	2026-05-20	2026-05-20
Context window	1,000,000 tokens	2,000,000 tokens	1,000,000 tokens	2,000,000 tokens
Parameters	400B	—	—	—
Modality	text, vision	text, vision, audio, video	text, vision, audio, video	text, vision, audio, video
License	Llama 4 Community License	proprietary	proprietary	proprietary
Source	open weights	proprietary	proprietary	proprietary
Description	Mixture-of-experts open-weight model from Meta.	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.	Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.
Links	weights →	vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	80.5%	87.1%	—	88.9%
GPQA-D	—	88.6%	—	91.2%
HumanEval	—	96.5%	—	—
Aider	—	84.8%	—	—
AIME-25	—	92.8%	—	96.1%
LiveCB	—	76.1%	—	—
MMMU	68.5%	84.3%	82.5%	86.0%