Compare AI models

Specifications
Parameters
>1T—
Context window
256k—
Benchmarks
Humanity's Last Exam · with tools
49.8%44.4%
Overview
CompanyQwenSpaceXSI
Release dateJan 26 2026Jul 9 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Grok 4 Heavy on 1 of the 1 benchmark they both report (Humanity's Last Exam). Grok 4 Heavy shipped 201 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Humanity's Last Exam · with tools, Qwen3-Max-Thinking leads at 49.8% vs Grok 4 Heavy at 44.4%.