Coding benchmark
Kimi Code Bench v2 leaderboard
Every model the catalog carries a published Kimi Code Bench v2 value for, ranked by that value.
CategoryCoding
MeasureCoding-agent pass rate
TasksRealistic coding-agent tasks
DifficultyProduction software engineering
Published byKimi K2.7 Code
A Moonshot AI internal coding-agent benchmark for realistic software-engineering tasks across mainstream programming languages and production technology stacks.
Kimi Code Bench v2 ranking
2 models with a published Kimi Code Bench v2 value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Coding-agent pass rate |
|---|---|---|---|
| 1 |  Kimi K3 | Moonshot AI | 72.9 |
| 2 | Kimi K2.7 Code | Moonshot AI | 62.0 |
Evidence key: Observed
Rows are ordered by the value Kimi K2.7 Code published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.