Compare AI models

Specifications
Parameters
1T14B
Context window
128k2k
API pricing
Cheapest input
$0.57Novita—
Cheapest output
$2.30Novita—
$229Novita · fp8—
Benchmarks
MMLU
89.5%66.3%
Overview
CompanyMoonshot AIQwen
Release dateJul 11 2025Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 leads Qwen-14B on 1 of the 1 benchmark they both report (MMLU). Qwen-14B shipped 655 days before Kimi K2, so benchmark comparisons should account for the intervening progress.

Kimi K2 has 1T parameters, while Qwen-14B has 14B. Context windows are 128k (Kimi K2) vs 2k (Qwen-14B).

On MMLU, Kimi K2 leads at 89.5% vs Qwen-14B at 66.3%.