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

o3×

Llama 4 Maverick×

DeepSeek-V4-Flash×

Claude 4.6 Sonnet×Clear all

	o3 OpenAI	Llama 4 Maverick Meta	DeepSeek-V4-Flash DeepSeek	Claude 4.6 Sonnet Anthropic
Vendor	OpenAI	Meta	DeepSeek	Anthropic
Family	o-series	Llama	DeepSeek	Claude
Release date	2025-04-16	2025-04-05	2026-04-22	2026-02-17
Context window	200,000 tokens	1,000,000 tokens	1,000,000 tokens	1,000,000 tokens
Parameters	—	400B	284B (13B active)	—
Modality	text, vision	text, vision	text	text, vision
License	proprietary	Llama 4 Community License	MIT	proprietary
Source	proprietary	open weights	open weights	proprietary
Description	Reasoning-focused model in the o-series.	Mixture-of-experts open-weight model from Meta.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.	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.
Links		weights →	weights →
Benchmarks
MMLU-Pro	—	80.5%	—	85.4%
GPQA-D	87.7%	—	—	85.8%
HumanEval	—	—	—	95.9%
Aider	—	—	—	83.6%
AIME-25	88.9%	—	—	87.4%
LiveCB	—	—	—	73.8%
MMMU	—	68.5%	—	—