Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Selected

Qwen3.6-27B×

Mistral Large 2×

DeepSeek-V4-Pro×

GPT-5.5×Clear all

	Qwen3.6-27B Alibaba	Mistral Large 2 Mistral	DeepSeek-V4-Pro DeepSeek	GPT-5.5 OpenAI
Vendor	Alibaba	Mistral	DeepSeek	OpenAI
Family	Qwen	Mistral	DeepSeek	GPT
Release date	2026-04-22	2024-07-24	2026-04-22	2026-04-23
Context window	262,144 tokens	128,000 tokens	1,000,000 tokens	400,000 tokens
Parameters	27B (dense)	123B	1.6T (49B active)	—
Modality	text, vision, video	text	text	text, vision, audio
License	Apache-2.0	Mistral Research License	MIT	proprietary
Source	open weights	open weights	open weights	proprietary
Description	Alibaba's first dense open-weight in the 3.6 family. Strong agentic-coding scores (77.2 SWE-bench Verified, matching Claude 4.5 Opus on Terminal-Bench 2.0). Supports 201 languages and multimodal text/image/video input.	—	DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs.	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 →	weights →	weights →	vendor →