Kimi K2.6 (High): benchmark results

Provider: Moonshot. Released 2026-04-20. Access: Open.

Unified ELO 1665 ± 1, rank #125 of 2032 rated models, from 18 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
OpenCompass LLM - Math75.7Score (%)85.7
OpenCompass Math - College82.7Score (%)85.7
ATOBench - Basket (Native)60Grounded verification rate (%; the resource-ownership contra75
OpenCompass Reasoning - Common78.1Score (%)75
OpenCompass Knowledge - Humanities92.5Score (%)67.9
SlopCodeBench18.88Isolated Solved (%)62.5
OpenCompass Knowledge - Engineering90.8Score (%)60.7
OpenCompass Math - Competition68.6Score (%)60.7
OpenCompass Knowledge - Common Sense89.6Score (%)57.1
ATOBench - JWT (Native)86.7Grounded verification rate (%; the reusable-artifact contrac50
OpenCompass LLM - Knowledge89.8Score (%)50
OpenCompass LLM - Reasoning62.9Score (%)50

Interactive version: theaggregate.ai/model?slug=kimi-k2-6-high · How It Works · Data refreshed daily, snapshot 2026-09-26.