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×

Llama 4 Maverick×

GPT-5×

Mistral Large 2×Clear all

	Gemini 3.5 Google	Llama 4 Maverick Meta	GPT-5 OpenAI	Mistral Large 2 Mistral
Vendor	Google	Meta	OpenAI	Mistral
Family	Gemini	Llama	GPT	Mistral
Release date	2026-05-20	2025-04-05	2025-08-07	2024-07-24
Context window	2,000,000 tokens	1,000,000 tokens	400,000 tokens	128,000 tokens
Parameters	—	400B	—	123B
Modality	text, vision, audio, video	text, vision	text, vision, audio	text
License	proprietary	Llama 4 Community License	proprietary	Mistral Research License
Source	proprietary	open weights	proprietary	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.	Mixture-of-experts open-weight model from Meta.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	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 →	weights →	vendor →	vendor →weights →
Benchmarks
MMLU-Pro	88.9%	80.5%	85.1%	—
GPQA-D	91.2%	—	87.3%	—
HumanEval	—	—	95.2%	89.0%
Aider	—	—	85.4%	—
AIME-25	96.1%	—	91.0%	—
LiveCB	—	—	74.5%	—
MMMU	86.0%	68.5%	74.1%	—