Kimi K2 (Preview): benchmark results

Provider: Moonshot. Released 2025-07-11.

Aggregate Rating 1704 ± 47, rank #307 of 10516 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
WuYuEval - Expert Module - Elo1991.94Elo rating from pairwise judged comparisons96.9
WuYuEval - Expert Module - Judge Score0.85Mean anchor-calibrated LLM-as-a-judge score (0-1)87.5
WuYuEval - Foundation Module - Accuracy92Accuracy (%)87.5
WuYuEval - Foundation Module - Macro-F192.85Macro-F1 (%)84.4
A.S.E (AICGSecEval)55.29Overall weighted score (0-100)80.6
A.S.E (AICGSecEval) - Quality79.9Code quality score (%)77.8
A.S.E (AICGSecEval) - Security37.82Code security score (%)69.4

Interactive version: theaggregate.ai/model?slug=kimi-k2-preview · How It Works · Data refreshed daily, snapshot 2026-11-21.