Compare AI models

Specifications
Parameters
7B/14B—
Context window
1M256k
Benchmarks
LiveCodeBench
38.6%79%
Overview
CompanyQwenSpaceXSI
Release dateJan 27 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads Qwen2.5-1M on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-1M shipped 163 days before Grok 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-1M) vs 256k (Grok 4). Qwen2.5-1M is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs Qwen2.5-1M at 38.6%.