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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MCP-Mark) | 81.1 | Score (%) | 100 |
| AA Omniscience - Science, Engineering & Mathematics | 44.8 | Accuracy (%) | 93.3 |
| AA Omniscience - Software Engineering (SWE) - PHP | 72 | Accuracy (%) | 93.2 |
| AA GPQA Diamond | 89.6 | Accuracy (%) | 93 |
| Artificial Analysis Intelligence Index | 41.95 | Intelligence Index | 92.3 |
| OTIS Mock AIME 2024-25 | 96.39 | Accuracy (%) | 92.3 |
| AA Omniscience - Software Engineering (SWE) - C | 76 | Accuracy (%) | 92 |
| AA Terminal-Bench Hard | 44.7 | Accuracy (%) | 91.9 |
| AA Humanity's Last Exam | 32.76 | Accuracy (%) | 91.8 |
| Design Arena (Website) | 1301 | Elo | 91.7 |
| AA CritPt | 10 | Accuracy (%) | 91.6 |
| AA Omniscience - Software Engineering (SWE) - Julia | 52 | Accuracy (%) | 90.2 |
Interactive version: theaggregate.ai/model?slug=kimi-k2-7-code · How the rankings work · Data refreshed daily, snapshot 2026-07-22.