Compare AI models

Specifications
Parameters
671B1T
Context window
128k256k
API pricing
Cheapest input
—$0.60Novita
Cheapest output
—$2.50Novita
—$245Novita · fp8
Benchmarks
SWE-Bench Verified
49.2%65.8%
GPQA Diamond
71.5%75.1%
Overview
CompanyDeepSeekMoonshot AI
Release dateJan 20 2025Sep 5 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 (0905) leads DeepSeek R1 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). DeepSeek R1 shipped 228 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Kimi K2 (0905) has 1T. Context windows are 128k (DeepSeek R1) vs 256k (Kimi K2 (0905)).

On SWE-Bench Verified, Kimi K2 (0905) leads at 65.8% vs DeepSeek R1 at 49.2%. On GPQA Diamond, Kimi K2 (0905) leads at 75.1% vs DeepSeek R1 at 71.5%.