Moonshot AI · LIVEBENCH 2026-11-06
kimi-k3.1-pro
Published benchmark results for this specific model configuration.
kimi-k3.1-proOverall score72.6 / 100
Cost / successful task$1.015USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
long agentic38.7reasoning91.1coding67.8browser75.9data analysis79.1research82.1design73.7
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.