Compare AI models

Specifications
Parameters
671B16B
Context window
128k8k
API pricing
Cheapest input
$0.25DeepInfra—
Cheapest output
$0.95DeepInfra—
$97.50DeepInfra · fp4—
Benchmarks
LiveCodeBench
74.8%14.3%
GPQA Diamond
80.1%35.2%
MMLU-Pro
84.8%42.4%
Overview
CompanyDeepSeekMoonshot AI
Release dateAug 21 2025Feb 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.1 leads Moonlight on 3 of the 3 benchmarks they both report (LiveCodeBench, GPQA Diamond, MMLU-Pro). Moonlight shipped 180 days before DeepSeek V3.1, so benchmark comparisons should account for the intervening progress.

DeepSeek V3.1 has 671B parameters, while Moonlight has 16B. Context windows are 128k (DeepSeek V3.1) vs 8k (Moonlight).

On LiveCodeBench, DeepSeek V3.1 leads at 74.8% vs Moonlight at 14.3%. On GPQA Diamond, DeepSeek V3.1 leads at 80.1% vs Moonlight at 35.2%. On MMLU-Pro, DeepSeek V3.1 leads at 84.8% vs Moonlight at 42.4%.