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

Qwen3 235B×

Qwen3.6-27B×

GPT-5.5×

Claude 4.6 Sonnet×Clear all

	Qwen3 235B Alibaba	Qwen3.6-27B Alibaba	GPT-5.5 OpenAI	Claude 4.6 Sonnet Anthropic
Vendor	Alibaba	Alibaba	OpenAI	Anthropic
Family	Qwen	Qwen	GPT	Claude
Release date	2025-04-29	2026-04-22	2026-04-23	2026-02-17
Context window	128,000 tokens	262,144 tokens	400,000 tokens	1,000,000 tokens
Parameters	235B	27B (dense)	—	—
Modality	text	text, vision, video	text, vision, audio	text, vision
License	Apache-2.0	Apache-2.0	proprietary	proprietary
Source	open weights	open weights	proprietary	proprietary
Description	Predecessor to the Qwen3.6 family.	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.	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.	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.
Links	weights →	weights →	vendor →
Benchmarks
MMLU-Pro	—	78.9%	87.6%	85.4%
GPQA-D	—	—	89.4%	85.8%
HumanEval	—	91.5%	96.8%	95.9%
Aider	—	70.2%	89.7%	83.6%
AIME-25	—	—	94.2%	87.4%
LiveCB	—	—	78.9%	73.8%
MMMU	—	70.3%	78.4%	—