Compare AI models

Specifications
Parameters
1T744B
Context window
256k—
API pricing
Input price
$0.95$1.00
Output price
$4.00$3.20
Cached input price
$0.16$0.20
Cheapest input
$0.50Chutes$0.60GMICloud
Cheapest output
$2.40DigitalOcean$1.92GMICloud
Benchmarks
BullshitBench v2
65%28%
SWE-Bench Verified
80.2%77.8%
BrowseComp
83.2%75.9%
Humanity's Last Exam · with tools
34.7%50.4%
GPQA Diamond
90.5%86%
Overview
CompanyMoonshot AIZ.ai
Release dateApr 21 2026Feb 12 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Kimi K2.6 leads GLM-5 on 4 of the 5 benchmarks they both report. Kimi K2.6 is cheaper on input: $0.95 vs $1.00 per million tokens. GLM-5 is cheaper on output: $3.20 vs $4.00 per million tokens. GLM-5 shipped 68 days before Kimi K2.6, so benchmark comparisons should account for the intervening progress.

Kimi K2.6 has 1T parameters, while GLM-5 has 744B.

On BullshitBench v2, Kimi K2.6 leads at 65% vs GLM-5 at 28%. On SWE-Bench Verified, Kimi K2.6 leads at 80.2% vs GLM-5 at 77.8%. On BrowseComp, Kimi K2.6 leads at 83.2% vs GLM-5 at 75.9%. On Humanity's Last Exam · with tools, GLM-5 leads at 50.4% vs Kimi K2.6 at 34.7%. On GPQA Diamond, Kimi K2.6 leads at 90.5% vs GLM-5 at 86%.