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×

GPT-5.5×

Llama 4 Maverick×

Mistral Large 2×Clear all

	Gemini 3.5 Google	GPT-5.5 OpenAI	Llama 4 Maverick Meta	Mistral Large 2 Mistral
Vendor	Google	OpenAI	Meta	Mistral
Family	Gemini	GPT	Llama	Mistral
Release date	2026-05-20	2026-04-23	2025-04-05	2024-07-24
Context window	2,000,000 tokens	400,000 tokens	1,000,000 tokens	128,000 tokens
Parameters	—	—	400B	123B
Modality	text, vision, audio, video	text, vision, audio	text, vision	text
License	proprietary	proprietary	Llama 4 Community License	Mistral Research License
Source	proprietary	proprietary	open weights	open weights
Description	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	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.	Mixture-of-experts open-weight model from Meta.	Large text-only Mistral model with a 128K context window and 123B parameters, tuned for strong instruction following and long-context reasoning. Mistral's flagship open-weights release in the Large 2 line.
Links	vendor →	vendor →	weights →	vendor →weights →
Benchmarks
MMLU-Pro	88.9%	87.6%	80.5%	—
GPQA-D	91.2%	89.4%	—	—
HumanEval	—	96.8%	—	89.0%
Aider	—	89.7%	—	—
AIME-25	96.1%	94.2%	—	—
LiveCB	—	78.9%	—	—
MMMU	86.0%	78.4%	68.5%	—