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 3.5×

Gemini 3 Pro×

Llama 4 Maverick×

GPT-5.5×Clear all

	Gemini 3.5 Google	Gemini 3 Pro Google	Llama 4 Maverick Meta	GPT-5.5 OpenAI
Vendor	Google	Google	Meta	OpenAI
Family	Gemini	Gemini	Llama	GPT
Release date	2026-05-20	2026-04-22	2025-04-05	2026-04-23
Context window	2,000,000 tokens	2,000,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	—	—	400B	—
Modality	text, vision, audio, video	text, vision, audio, video	text, vision	text, vision, audio
License	proprietary	proprietary	Llama 4 Community License	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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.	Mixture-of-experts open-weight model from Meta.	OpenAI's smartest and most intuitive model — successor to GPT-5, with major coding, research, and document workflow gains. GPT-5.5 Pro variant also available for heavier reasoning.
Links	vendor →	vendor →	weights →	vendor →
Benchmarks
MMLU-Pro	88.9%	87.1%	80.5%	87.6%
GPQA-D	91.2%	88.6%	—	89.4%
HumanEval	—	96.5%	—	96.8%
Aider	—	84.8%	—	89.7%
AIME-25	96.1%	92.8%	—	94.2%
LiveCB	—	76.1%	—	78.9%
MMMU	86.0%	84.3%	68.5%	78.4%