Coding benchmark
PostTrain Bench leaderboard
Every model the catalog carries a published PostTrain Bench value for, ranked by that value.
CategoryCoding
MeasureHarbor agent evaluation
TasksPost-training software-engineering tasks
DifficultyFrontier software engineering
Published byKimi K3: Open Frontier Intelligence
A software-engineering benchmark for post-training infrastructure and implementation tasks, evaluated through the official Harbor implementation.
PostTrain Bench ranking
3 models with a published PostTrain Bench 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 | Harbor agent evaluation |
|---|---|---|---|
| 1 |  GLM-5.3 | Z.AI | 39.8 |
| 2 |  Kimi K3 | Moonshot AI | 36.6 |
| 3 |  Hy4 preview | Tencent | 35.6 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence 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.