MOONSHOT · MODEL TELEMETRY CARD

Kimi K2 Thinking

Canonical UID: moonshot/kimi-k2-thinking · Released: 2025-11-06

Measured configurations of Kimi K2 Thinking across benchmark suites. Exact machine values in site.json and data dumps.
Domain Benchmark Effort / Mode ⚡ Value/Cost # 🏆 Performance # Score Task $ Unit Cost $ Unit
Code ALE-Bench STD #65 / 94 #76 / 94 597.5 $0.087819 $0.000147 rating point

Compare against all models on ← #frontier Live Ranking Board · Fixed-capability cost half-life analysis on /methodology.