Compare AI models

Specifications
Parameters
7B/14B—
Context window
1M1M
Benchmarks
LiveCodeBench
38.6%57%
Overview
CompanyQwenSpaceXSI
Release dateJan 27 2025Feb 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 3 leads Qwen2.5-1M on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-1M shipped 21 days before Grok 3, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Qwen2.5-1M) vs 1M (Grok 3). Qwen2.5-1M is open weight, while Grok 3 is closed.

On LiveCodeBench, Grok 3 leads at 57% vs Qwen2.5-1M at 38.6%.