Compare AI models

Specifications
Parameters
>1T—
Context window
256k128k
Benchmarks
MMLU-Pro
85.7%75.5%
Overview
CompanyQwenSpaceXSI
Release dateJan 26 2026Aug 13 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Qwen3-Max-Thinking leads Grok‑2 on 1 of the 1 benchmark they both report (MMLU-Pro). Grok‑2 shipped 531 days before Qwen3-Max-Thinking, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Qwen3-Max-Thinking) vs 128k (Grok‑2).

On MMLU-Pro, Qwen3-Max-Thinking leads at 85.7% vs Grok‑2 at 75.5%.