Compare AI models

Specifications
Parameters
27B/35B/122B—
Context window
256k256k
Benchmarks
LiveCodeBench
78.9%79%
BrowseComp
63.8%43%
Humanity's Last Exam · no tools
25.3%25.4%
Humanity's Last Exam · with tools
47.5%38.6%
GPQA Diamond
86.6%87.5%
Overview
CompanyQwenSpaceXSI
Release dateFeb 24 2026Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads Qwen3.5 Medium on 3 of the 5 benchmarks they both report (LiveCodeBench, BrowseComp, Humanity's Last Exam, GPQA Diamond). Grok 4 shipped 230 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Qwen3.5 Medium) vs 256k (Grok 4). Qwen3.5 Medium is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs Qwen3.5 Medium at 78.9%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Grok 4 at 43%. On Humanity's Last Exam · no tools, Grok 4 leads at 25.4% vs Qwen3.5 Medium at 25.3%. On Humanity's Last Exam · with tools, Qwen3.5 Medium leads at 47.5% vs Grok 4 at 38.6%. On GPQA Diamond, Grok 4 leads at 87.5% vs Qwen3.5 Medium at 86.6%.