Compare AI models

Specifications
Parameters
1T7B/14B
Context window
256k1M
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · fp8—
Benchmarks
MMLU-Pro
81.9%63.3%
Overview
CompanyMoonshot AIQwen
Release dateSep 5 2025Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 (0905) leads Qwen2.5-1M on 1 of the 1 benchmark they both report (MMLU-Pro). Qwen2.5-1M shipped 221 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.

Kimi K2 (0905) has 1T parameters, while Qwen2.5-1M has 7B/14B. Context windows are 256k (Kimi K2 (0905)) vs 1M (Qwen2.5-1M).

On MMLU-Pro, Kimi K2 (0905) leads at 81.9% vs Qwen2.5-1M at 63.3%.