Compare AI models

Specifications
Parameters
16B—
Context window
8k128k
Benchmarks
HumanEval
48.1%74.1%
MATH
45.3%50.6%
MMLU-Pro
42.4%51%
MMLU
70%81.3%
GSM8K
77.4%90%
Overview
CompanyMoonshot AISpaceXSI
Release dateFeb 22 2025Mar 28 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok‑1.5 leads Moonlight on 5 of the 5 benchmarks they both report. Grok‑1.5 shipped 331 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Moonlight) vs 128k (Grok‑1.5). Moonlight is open weight, while Grok‑1.5 is closed.

On HumanEval, Grok‑1.5 leads at 74.1% vs Moonlight at 48.1%. On MATH, Grok‑1.5 leads at 50.6% vs Moonlight at 45.3%. On MMLU-Pro, Grok‑1.5 leads at 51% vs Moonlight at 42.4%. On MMLU, Grok‑1.5 leads at 81.3% vs Moonlight at 70%. On GSM8K, Grok‑1.5 leads at 90% vs Moonlight at 77.4%.