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×

GPT-5.6 Sol×

Qwen3.7-Max×

GPT-5 Pro×Clear all

	Qwen3 235B Alibaba	GPT-5.6 Sol OpenAI	Qwen3.7-Max Alibaba	GPT-5 Pro OpenAI
Vendor	Alibaba	OpenAI	Alibaba	OpenAI
Family	Qwen	GPT	Qwen	GPT
Release date	2025-04-29	2026-06-26	2026-05-20	2025-08-07
Context window	128,000 tokens	—	1,000,000 tokens	400,000 tokens
Parameters	235B	—	—	—
Modality	text	text, vision, audio	text	text, vision, audio
License	Apache-2.0	proprietary	proprietary	proprietary
Source	open weights	proprietary	proprietary	proprietary
Description	Predecessor to the Qwen3.6 family.	Flagship of OpenAI's GPT-5.6 three-model suite (Sol / Terra / Luna), released as a limited preview. Strong gains in coding, cybersecurity, biology, and long-horizon agentic work. Pricing: $5 / $30 per million input/output tokens.	Alibaba's flagship agent model — 1M-token context, extended-thinking mode, 56.6 on the Artificial Analysis Intelligence Index v4.0 (5th overall, #1 Chinese). 50.8% on Terminal-Bench Hard. Designed for long-horizon agent workloads (hundreds-to-thousands of steps). Closed-weight, $2.50/$7.50 per 1M tokens.	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.
Links	weights →	vendor →	vendor →	vendor →
Benchmarks
MMLU-Pro	—	—	83.7%	—
GPQA-D	—	—	83.0%	—
HumanEval	—	—	93.9%	—
Aider	—	—	78.4%	—
AIME-25	—	—	90.4%	—
LiveCB	—	—	71.0%	—