EvalLedger
LeaderboardCompareToken CalculatorModel ReleasesVersion seriesChangelog
Moonshot·other·k3

Kimi K3

Updated: 2026-10-19
—

Benchmark scores

GPQA Diamond92.9%
HLE43.5%
MathArena Apex65.6%
Terminal-Bench 2.188.3%
Terminal-Bench 3.017.7%
Terminal-Bench 4.012.6%
DeepSWE v1.167.5%
ProgramBench17.5%
NL2Repo-Bench58%
CyberGym80%
HLE (w/tools)59.8%
Automation-Bench46.7%
Agents' Last Exam27.6%
Chartography (w/tools)68.1%
BabyVision (w/tools)85.7%
ZeroBench-main (w/tools)41%

Pricing

—Run your usage →

Comparisons

GPT 5.6-Sol vs Kimi K3DeepSeek V4.1-Flash 0910 vs Kimi K3Grok 4.7 vs Kimi K3GLM 5.3 vs Kimi K3
EvalLedger

Pricing, benchmarks, and version history for every major LLM.

Product

LeaderboardCompareToken Calculator

Resources

X (Twitter)Model ReleasesChangelog

Legal

TermsPrivacyContact

© 2026 EvalLedger. © 2026 EvalLedger. All rights reserved.