Moonshot AIProvisional

Kimi K2.7 Code

Kimi / Kimi K2.7 Code · moonshotai/Kimi-K2.7-Code

Coding-focused agentic Kimi model for long-horizon software engineering workflows.

Objective score

39.5

Confidence

85%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

Kimi K2.6Kimi K2.7 Code

Scenario evidence

Six task-specific rankings

Feature development#32Obj. 39.50 · 0%Debug and repair#33Obj. 48.70 · 0%Refactoring#32Obj. 49.50 · 0%Code review#30Obj. 50.60 · 0%Large-repo agent work#45Obj. 24.70 · 0%Frontend / UI#32Obj. 48.70 · 0%

Evidence state

Signal coverage

Benchmarks: 3
Rank points: 7
Usage: 2
Agent: 0
Sources: 5

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: 59.1
Artificial Analysis: 60.8
Openrouter Usage: 1
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#23 · 40

Aug 1#23 · 40

Jul 31#23 · 40

Jul 31#23 · 40

Jul 31#23 · 40

Jul 31#23 · 40

Usage signals

OpenRouter1%

Overall0.7%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

Official Moonshot model card describes K2.7 Code as coding-focused agentic model.Artificial Analysis Coding Agents · ok WebDev Arena · ok Kilo leaderboard · ok Kimi K2.7 Code model card · ok Kimi API models · ok