Compare AI models

Specifications
Parameters
1T9B/32B
Context window
256k128k
API pricing
Cheapest input
$0.60Novita—
Cheapest output
$2.50Novita—
$245Novita · bf16—
Benchmarks
LiveCodeBench
83.1%59.1%
AIME 2025
94.5%63.6%
Overview
CompanyMoonshot AIZ.ai
Release dateNov 6 2025Apr 14 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2 Thinking leads GLM-Z1-0414 on 2 of the 2 benchmarks they both report (LiveCodeBench, AIME 2025). GLM-Z1-0414 shipped 206 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.

Kimi K2 Thinking has 1T parameters, while GLM-Z1-0414 has 9B/32B. Context windows are 256k (Kimi K2 Thinking) vs 128k (GLM-Z1-0414).

On LiveCodeBench, Kimi K2 Thinking leads at 83.1% vs GLM-Z1-0414 at 59.1%. On AIME 2025, Kimi K2 Thinking leads at 94.5% vs GLM-Z1-0414 at 63.6%.