Compare AI models

Specifications
Parameters
1T14.3B
Context window
128k32k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
MMLU
89.5%62.5%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 leads Qwen1.5-MoE on 1 of the 1 benchmark they both report (MMLU). Qwen1.5-MoE shipped 470 days before Kimi K2, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen1.5-MoE has 14.3B. Context windows are 128k (Kimi K2) vs 32k (Qwen1.5-MoE).

On MMLU, Kimi K2 leads at 89.5% vs Qwen1.5-MoE at 62.5%.