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

GPT-5.5×

Gemini 3.5×

DeepSeek-V4-Flash×

Qwen3.6-27B×Clear all

	GPT-5.5 OpenAI	Gemini 3.5 Google	DeepSeek-V4-Flash DeepSeek	Qwen3.6-27B Alibaba
Vendor	OpenAI	Google	DeepSeek	Alibaba
Family	GPT	Gemini	DeepSeek	Qwen
Release date	2026-04-23	2026-05-20	2026-04-22	2026-04-22
Context window	400,000 tokens	2,000,000 tokens	1,000,000 tokens	262,144 tokens
Parameters	—	—	284B (13B active)	27B (dense)
Modality	text, vision, audio	text, vision, audio, video	text	text, vision, video
License	proprietary	proprietary	MIT	Apache-2.0
Source	proprietary	proprietary	open weights	open weights
Description	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.	Google DeepMind's next-gen Gemini — positioned as "frontier intelligence with action". Built for complex agentic workflows. Announced at Google I/O 2026.	Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE.	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.
Links	vendor →	vendor →	weights →	weights →
Benchmarks
MMLU-Pro	87.6%	88.9%	—	78.9%
GPQA-D	89.4%	91.2%	—	—
HumanEval	96.8%	—	—	91.5%
Aider	89.7%	—	—	70.2%
AIME-25	94.2%	96.1%	—	—
LiveCB	78.9%	—	—	—
MMMU	78.4%	86.0%	—	70.3%