Compare AI models

Specifications
Parameters
14.3B314B
Context window
32k8k
Benchmarks
HumanEval
34.2%63.2%
MMLU
62.5%73%
GSM8K
61.5%62.9%
Overview
CompanyQwenSpaceXSI
Release dateMar 28 2024Nov 3 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Grok‑1 leads Qwen1.5-MoE on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Grok‑1 shipped 146 days before Qwen1.5-MoE, so benchmark comparisons should account for the intervening progress.

Qwen1.5-MoE has 14.3B parameters, while Grok‑1 has 314B. Context windows are 32k (Qwen1.5-MoE) vs 8k (Grok‑1).

On HumanEval, Grok‑1 leads at 63.2% vs Qwen1.5-MoE at 34.2%. On MMLU, Grok‑1 leads at 73% vs Qwen1.5-MoE at 62.5%. On GSM8K, Grok‑1 leads at 62.9% vs Qwen1.5-MoE at 61.5%.