Compare AI models

Specifications
Parameters
27B/35B/122B—
Context window
256k2M
Benchmarks
LiveCodeBench
78.9%80%
BrowseComp
63.8%44.9%
Humanity's Last Exam · no tools
25.3%20%
GPQA Diamond
86.6%85.7%
Overview
CompanyQwenSpaceXSI
Release dateFeb 24 2026Sep 19 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen3.5 Medium leads Grok 4 Fast on 3 of the 4 benchmarks they both report (LiveCodeBench, BrowseComp, Humanity's Last Exam, GPQA Diamond). Grok 4 Fast shipped 158 days before Qwen3.5 Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Qwen3.5 Medium) vs 2M (Grok 4 Fast). Qwen3.5 Medium is open weight, while Grok 4 Fast is closed.

On LiveCodeBench, Grok 4 Fast leads at 80% vs Qwen3.5 Medium at 78.9%. On BrowseComp, Qwen3.5 Medium leads at 63.8% vs Grok 4 Fast at 44.9%. On Humanity's Last Exam · no tools, Qwen3.5 Medium leads at 25.3% vs Grok 4 Fast at 20%. On GPQA Diamond, Qwen3.5 Medium leads at 86.6% vs Grok 4 Fast at 85.7%.