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×

Claude 4.6 Sonnet×

GPT-5×

DeepSeek-V3.1×Clear all

	Llama 4 Maverick Meta	Claude 4.6 Sonnet Anthropic	GPT-5 OpenAI	DeepSeek-V3.1 DeepSeek
Vendor	Meta	Anthropic	OpenAI	DeepSeek
Family	Llama	Claude	GPT	DeepSeek
Release date	2025-04-05	2026-02-17	2025-08-07	2025-08-21
Context window	1,000,000 tokens	1,000,000 tokens	400,000 tokens	128,000 tokens
Parameters	400B	—	—	671B
Modality	text, vision	text, vision	text, vision, audio	text
License	Llama 4 Community License	proprietary	proprietary	MIT
Source	open weights	proprietary	proprietary	open weights
Description	Mixture-of-experts open-weight model from Meta.	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.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.	Large MoE open-weight model. Predecessor to DeepSeek-V4.
Links	weights →		vendor →	weights →
Benchmarks
MMLU-Pro	80.5%	85.4%	85.1%	—
GPQA-D	—	85.8%	87.3%	—
HumanEval	—	95.9%	95.2%	—
Aider	—	83.6%	85.4%	—
AIME-25	—	87.4%	91.0%	—
LiveCB	—	73.8%	74.5%	—
MMMU	68.5%	—	74.1%	—