Compare AI models

Specifications
Parameters
14.3B—
Context window
32k128k
Benchmarks
HumanEval
34.2%88.4%
MMLU
62.5%87.5%
Overview
CompanyQwenSpaceXSI
Release dateMar 28 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 leads Qwen1.5-MoE on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen1.5-MoE shipped 138 days before Grok‑2, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Qwen1.5-MoE) vs 128k (Grok‑2). Qwen1.5-MoE is open weight, while Grok‑2 is closed.

On HumanEval, Grok‑2 leads at 88.4% vs Qwen1.5-MoE at 34.2%. On MMLU, Grok‑2 leads at 87.5% vs Qwen1.5-MoE at 62.5%.