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×

Qwen3 235B×

Mistral Large 2×

Llama 4 Maverick×Clear all

	DeepSeek-V3.1 DeepSeek	Qwen3 235B Alibaba	Mistral Large 2 Mistral	Llama 4 Maverick Meta
Vendor	DeepSeek	Alibaba	Mistral	Meta
Family	DeepSeek	Qwen	Mistral	Llama
Release date	2025-08-21	2025-04-29	2024-07-24	2025-04-05
Context window	128,000 tokens	128,000 tokens	128,000 tokens	1,000,000 tokens
Parameters	671B	235B	123B	400B
Modality	text	text	text	text, vision
License	MIT	Apache-2.0	Mistral Research License	Llama 4 Community License
Source	open weights	open weights	open weights	open weights
Description	Large MoE open-weight model. Predecessor to DeepSeek-V4.	Predecessor to the Qwen3.6 family.	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.	Mixture-of-experts open-weight model from Meta.
Links	weights →	weights →	vendor →weights →	weights →
Benchmarks
MMLU-Pro	—	—	—	80.5%
HumanEval	—	—	89.0%	—
MMMU	—	—	—	68.5%