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

Claude 4.6 Sonnet×

o3×

Llama 4 Maverick×

GPT-5.5×Clear all

	Claude 4.6 Sonnet Anthropic	o3 OpenAI	Llama 4 Maverick Meta	GPT-5.5 OpenAI
Vendor	Anthropic	OpenAI	Meta	OpenAI
Family	Claude	o-series	Llama	GPT
Release date	2026-02-17	2025-04-16	2025-04-05	2026-04-23
Context window	1,000,000 tokens	200,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	—	—	400B	—
Modality	text, vision	text, vision	text, vision	text, vision, audio
License	proprietary	proprietary	Llama 4 Community License	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	Reasoning-focused model in the o-series.	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			weights →	vendor →
Benchmarks
MMLU-Pro	85.4%	—	80.5%	87.6%
GPQA-D	85.8%	87.7%	—	89.4%
HumanEval	95.9%	—	—	96.8%
Aider	83.6%	—	—	89.7%
AIME-25	87.4%	88.9%	—	94.2%
LiveCB	73.8%	—	—	78.9%
MMMU	—	—	68.5%	78.4%