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 Pro×

Qwen3 235B×

GPT-5.5×

Qwen3.6-27B×Clear all

	GPT-5 Pro OpenAI	Qwen3 235B Alibaba	GPT-5.5 OpenAI	Qwen3.6-27B Alibaba
Vendor	OpenAI	Alibaba	OpenAI	Alibaba
Family	GPT	Qwen	GPT	Qwen
Release date	2025-08-07	2025-04-29	2026-04-23	2026-04-22
Context window	400,000 tokens	128,000 tokens	400,000 tokens	262,144 tokens
Parameters	—	235B	—	27B (dense)
Modality	text, vision, audio	text	text, vision, audio	text, vision, video
License	proprietary	Apache-2.0	proprietary	Apache-2.0
Source	proprietary	open weights	proprietary	open weights
Description	Higher-reasoning variant of GPT-5, used for harder scientific and research tasks (e.g., immunology breakthroughs at NIH). Same 400K context as GPT-5; trades latency for depth.	Predecessor to the Qwen3.6 family.	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.	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 →	weights →	vendor →	weights →
Benchmarks
MMLU-Pro	—	—	87.6%	78.9%
GPQA-D	—	—	89.4%	—
HumanEval	—	—	96.8%	91.5%
Aider	—	—	89.7%	70.2%
AIME-25	—	—	94.2%	—
LiveCB	—	—	78.9%	—
MMMU	—	—	78.4%	70.3%