Compare AI models

Specifications
Parameters
14B—
Context window
2k128k
Benchmarks
HumanEval
32.3%88.4%
MATH
24.8%76.1%
MMLU
66.3%87.5%
Overview
CompanyQwenSpaceXSI
Release dateSep 25 2023Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 leads Qwen-14B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Qwen-14B shipped 323 days before Grok‑2, so benchmark comparisons should account for the intervening progress.

Context windows are 2k (Qwen-14B) vs 128k (Grok‑2). Qwen-14B is open weight, while Grok‑2 is closed.

On HumanEval, Grok‑2 leads at 88.4% vs Qwen-14B at 32.3%. On MATH, Grok‑2 leads at 76.1% vs Qwen-14B at 24.8%. On MMLU, Grok‑2 leads at 87.5% vs Qwen-14B at 66.3%.