Compare AI models

Specifications
Parameters
0.5B/1.8B/4B/7B/14B/72B—
Context window
32k—
Benchmarks
HumanEval
71.3%85.7%
MMLU-Pro
51.7%72%
MMLU
75.6%86.2%
Overview
CompanyQwenSpaceXSI
Release dateFeb 4 2024Aug 13 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑2 mini leads Qwen1.5 on 3 of the 3 benchmarks they both report (HumanEval, MMLU-Pro, MMLU). Qwen1.5 shipped 191 days before Grok‑2 mini, so benchmark comparisons should account for the intervening progress.

Qwen1.5 is open weight, while Grok‑2 mini is closed.

On HumanEval, Grok‑2 mini leads at 85.7% vs Qwen1.5 at 71.3%. On MMLU-Pro, Grok‑2 mini leads at 72% vs Qwen1.5 at 51.7%. On MMLU, Grok‑2 mini leads at 86.2% vs Qwen1.5 at 75.6%.