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

DeepSeek-V3.1×

DeepSeek-R1×

Claude 4.6 Sonnet×

Llama 4 Maverick×Clear all

	DeepSeek-V3.1 DeepSeek	DeepSeek-R1 DeepSeek	Claude 4.6 Sonnet Anthropic	Llama 4 Maverick Meta
Vendor	DeepSeek	DeepSeek	Anthropic	Meta
Family	DeepSeek	DeepSeek	Claude	Llama
Release date	2025-08-21	2025-01-20	2026-02-17	2025-04-05
Context window	128,000 tokens	128,000 tokens	1,000,000 tokens	1,000,000 tokens
Parameters	671B	671B	—	400B
Modality	text	text	text, vision	text, vision
License	MIT	MIT	proprietary	Llama 4 Community License
Source	open weights	open weights	proprietary	open weights
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	Reasoning-focused open-weight model.	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.	Mixture-of-experts open-weight model from Meta.
Links	weights →	weights →		weights →
Benchmarks
MMLU-Pro	—	—	85.4%	80.5%
GPQA-D	—	—	85.8%	—
HumanEval	—	—	95.9%	—
Aider	—	—	83.6%	—
AIME-25	—	79.8%	87.4%	—
LiveCB	—	—	73.8%	—
MMMU	—	—	—	68.5%