Compare AI models

Specifications
Parameters
1T4B
Context window
128k256k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
MATH-500
97.4%95.4%
GPQA Diamond
75.1%53.2%
Overview
CompanyMoonshot AINVIDIA
Release dateJul 11 2025Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 leads Nemotron 3 Nano 4B on 2 of the 2 benchmarks they both report (MATH-500, GPQA Diamond). Kimi K2 shipped 248 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Nemotron 3 Nano 4B has 4B. Context windows are 128k (Kimi K2) vs 256k (Nemotron 3 Nano 4B).

On MATH-500, Kimi K2 leads at 97.4% vs Nemotron 3 Nano 4B at 95.4%. On GPQA Diamond, Kimi K2 leads at 75.1% vs Nemotron 3 Nano 4B at 53.2%.