Compare AI models

Specifications
Parameters
1T4B
Context window
256k256k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
AIME 2025
94.5%78.5%
GPQA Diamond
84.5%53.2%
Overview
CompanyMoonshot AINVIDIA
Release dateNov 6 2025Mar 16 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads Nemotron 3 Nano 4B on 2 of the 2 benchmarks they both report (AIME 2025, GPQA Diamond). Kimi K2 Thinking shipped 130 days before Nemotron 3 Nano 4B, so benchmark comparisons should account for the intervening progress.

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

On AIME 2025, Kimi K2 Thinking leads at 94.5% vs Nemotron 3 Nano 4B at 78.5%. On GPQA Diamond, Kimi K2 Thinking leads at 84.5% vs Nemotron 3 Nano 4B at 53.2%.