Compare AI models

Specifications
Parameters
110B—
Context window
32k128k
Benchmarks
HumanEval
52.4%74.1%
MATH
49.6%50.6%
MMLU
80.4%81.3%
GSM8K
85.4%90%
Overview
CompanyQwenSpaceXSI
Release dateApr 25 2024Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑1.5 leads Qwen1.5-110B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Grok‑1.5 shipped 28 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Qwen1.5-110B) vs 128k (Grok‑1.5). Qwen1.5-110B is open weight, while Grok‑1.5 is closed.

On HumanEval, Grok‑1.5 leads at 74.1% vs Qwen1.5-110B at 52.4%. On MATH, Grok‑1.5 leads at 50.6% vs Qwen1.5-110B at 49.6%. On MMLU, Grok‑1.5 leads at 81.3% vs Qwen1.5-110B at 80.4%. On GSM8K, Grok‑1.5 leads at 90% vs Qwen1.5-110B at 85.4%.