Compare AI models

Specifications
Parameters
14B314B
Context window
2k8k
Benchmarks
HumanEval
32.3%63.2%
MATH
24.8%23.9%
MMLU
66.3%73%
GSM8K
61.3%62.9%
Overview
CompanyQwenSpaceXSI
Release dateSep 25 2023Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 leads Qwen-14B on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 39 days before Grok‑1, so benchmark comparisons should account for the intervening progress.

Qwen-14B has 14B parameters, while Grok‑1 has 314B. Context windows are 2k (Qwen-14B) vs 8k (Grok‑1).

On HumanEval, Grok‑1 leads at 63.2% vs Qwen-14B at 32.3%. On MATH, Qwen-14B leads at 24.8% vs Grok‑1 at 23.9%. On MMLU, Grok‑1 leads at 73% vs Qwen-14B at 66.3%. On GSM8K, Grok‑1 leads at 62.9% vs Qwen-14B at 61.3%.