Compare AI models

Specifications
Parameters
16B4B/30B/235B
Context window
8k256k
Benchmarks
LiveCodeBench
14.3%74.1%
GPQA Diamond
35.2%81.1%
MMLU-Pro
42.4%84.4%
Overview
CompanyMoonshot AIQwen
Release dateFeb 22 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Moonlight on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Moonlight shipped 149 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

Moonlight has 16B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 8k (Moonlight) vs 256k (Qwen3-2507).

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Moonlight at 14.3%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Moonlight at 35.2%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Moonlight at 42.4%.