TestsBenchmarks · Coding
Kimi Code Bench v2 (internal)
Moonshot in-house realistic coding-agent benchmark across 10+ languages (vendor-internal).
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Kimi K3 | Moonshot AI (Kimi) | 72.9% | Maxreasoning_effort=max | Maker's own figureVendor-reportedMoonshot AI ↗ | Kimi Code | 16 Jul 2026 |
| 2 | Kimi K2.7 Code | Moonshot AI (Kimi) | 62.0% | Defaultthinking | Maker's own figureVendor-reportedMoonshot AI ↗ | Kimi Code CLI | 12 Jun 2026 |
| 3 | Kimi K2.6 | Moonshot AI (Kimi) | 50.9% | Defaultthinking | Maker's own figureVendor-reportedMoonshot AI ↗ | Kimi Code CLI | 12 Jun 2026 |