Compare AI models

Specifications
Parameters
1T4B
Context window
128k128k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
IFEval
89.8%75.5%
MATH-500
97.4%96.2%
GPQA Diamond
75.1%55.1%
Overview
CompanyMoonshot AINVIDIA
Release dateJul 11 2025May 20 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 leads Llama Nemotron Nano 4B v1.1 on 3 of the 3 benchmarks they both report (IFEval, MATH-500, GPQA Diamond). Llama Nemotron Nano 4B v1.1 shipped 52 days before Kimi K2, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Llama Nemotron Nano 4B v1.1 has 4B. Context windows are 128k (Kimi K2) vs 128k (Llama Nemotron Nano 4B v1.1).

On IFEval, Kimi K2 leads at 89.8% vs Llama Nemotron Nano 4B v1.1 at 75.5%. On MATH-500, Kimi K2 leads at 97.4% vs Llama Nemotron Nano 4B v1.1 at 96.2%. On GPQA Diamond, Kimi K2 leads at 75.1% vs Llama Nemotron Nano 4B v1.1 at 55.1%.