Kimi K2.7 Code — benchmark results

Moonshot's open coding-focused Kimi K2.7 Code MoE model (1T total, 32B active). Provider: Moonshot. Released 2026-06-12. Access: API.

Unified ELO 1814 ± 13, rank #128 of 1776 rated models, from 97 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (MCP-Mark)81.1Score (%)100
AA Omniscience - Science, Engineering & Mathematics44.8Accuracy (%)93.3
AA Omniscience - Software Engineering (SWE) - PHP72Accuracy (%)93.2
AA GPQA Diamond89.6Accuracy (%)93
Artificial Analysis Intelligence Index41.95Intelligence Index92.3
OTIS Mock AIME 2024-2596.39Accuracy (%)92.3
AA Omniscience - Software Engineering (SWE) - C76Accuracy (%)92
AA Terminal-Bench Hard44.7Accuracy (%)91.9
AA Humanity's Last Exam32.76Accuracy (%)91.8
Design Arena (Website)1301Elo91.7
AA CritPt10Accuracy (%)91.6
AA Omniscience - Software Engineering (SWE) - Julia52Accuracy (%)90.2

Interactive version: theaggregate.ai/model?slug=kimi-k2-7-code · How the rankings work · Data refreshed daily, snapshot 2026-07-22.