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×

Qwen3.6-27B×

DeepSeek-R1×Clear all

	GPT-5.5 OpenAI	Gemini 3.5 Google	Qwen3.6-27B Alibaba	DeepSeek-R1 DeepSeek
Vendor	OpenAI	Google	Alibaba	DeepSeek
Family	GPT	Gemini	Qwen	DeepSeek
Release date	2026-04-23	2026-05-20	2026-04-22	2025-01-20
Context window	400,000 tokens	2,000,000 tokens	262,144 tokens	128,000 tokens
Parameters	—	—	27B (dense)	671B
Modality	text, vision, audio	text, vision, audio, video	text, vision, video	text
License	proprietary	proprietary	Apache-2.0	MIT
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.	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.	Reasoning-focused open-weight model.
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%	—	79.8%
LiveCB	78.9%	—	—	—
MMMU	78.4%	86.0%	70.3%	—