Compare AI models

Specifications
Parameters
—16B
Context window
200k8k
Benchmarks
HumanEval
93.7%48.1%
GPQA Diamond
65%35.2%
MMLU
90.5%70%
Overview
CompanyAnthropicMoonshot AI
Release dateOct 22 2024Feb 22 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Sonnet (upgraded) leads Moonlight on 3 of the 3 benchmarks they both report (HumanEval, GPQA Diamond, MMLU). Claude 3.5 Sonnet (upgraded) shipped 123 days before Moonlight, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Sonnet (upgraded)) vs 8k (Moonlight). Claude 3.5 Sonnet (upgraded) is closed, while Moonlight is open weight.

On HumanEval, Claude 3.5 Sonnet (upgraded) leads at 93.7% vs Moonlight at 48.1%. On GPQA Diamond, Claude 3.5 Sonnet (upgraded) leads at 65% vs Moonlight at 35.2%. On MMLU, Claude 3.5 Sonnet (upgraded) leads at 90.5% vs Moonlight at 70%.