Compare AI models

Specifications
Parameters
16B117B
Context window
8k128k
API pricing
Cheapest input
—$0.03AkashML
Cheapest output
—$0.15Near AI
—$13.50Venice · int4
Benchmarks
GPQA Diamond
35.2%80.1%
MMLU
70%90%
Overview
CompanyMoonshot AIOpenAI
Release dateFeb 22 2025Aug 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

gpt-oss-120b leads Moonlight on 2 of the 2 benchmarks they both report (GPQA Diamond, MMLU). Moonlight shipped 164 days before gpt-oss-120b, so benchmark comparisons should account for the intervening progress.

Moonlight has 16B parameters, while gpt-oss-120b has 117B. Context windows are 8k (Moonlight) vs 128k (gpt-oss-120b).

On GPQA Diamond, gpt-oss-120b leads at 80.1% vs Moonlight at 35.2%. On MMLU, gpt-oss-120b leads at 90% vs Moonlight at 70%.