PostTrain Bench
We show this table for reference; we do not rank on it.
A software-engineering benchmark for post-training infrastructure and implementation tasks, evaluated through the official Harbor implementation.
Benchmark score on PostTrain Bench — September 27, 2026
We compile the PostTrain Bench rows from provider self-reports. GLM-5.3 leads the table at 39.8%, followed by Kimi K3 (36.6%) and Hy4 preview (35.6%). We do not use these results to rank models overall.
GLM-5.3
Z.AI
Kimi K3
Moonshot AI
Hy4 preview
Tencent
3 modelsCodingCurrentDisplay onlyUpdated September 27, 2026
Benchmark score table (3 models)
ScoreAmong the reported PostTrain Bench rows, GLM-5.3 is first at 39.8%. The third row is 4.2 points behind. The broader top-10 range is 4.2 points, so many of the published results sit in a relatively narrow band.
3 models have been evaluated on PostTrain Bench. The benchmark falls in the Coding category. PostTrain Bench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About PostTrain Bench
Year
2026
Tasks
Post-training software-engineering tasks
Format
Harbor agent evaluation
Difficulty
Frontier software engineering
Moonshot evaluates Kimi K3 at maximum reasoning effort with the official Harbor implementation and Claude Code harness, averaged over three runs. BenchLM stores the provider-exact value as display-only launch evidence.
Freshness and provenance
Version
PostTrain Bench 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does PostTrain Bench measure?
A software-engineering benchmark for post-training infrastructure and implementation tasks, evaluated through the official Harbor implementation.
Which model scores highest on PostTrain Bench?
GLM-5.3 by Z.AI currently leads with a score of 39.8% on PostTrain Bench.
How many models are evaluated on PostTrain Bench?
3 AI models have been evaluated on PostTrain Bench on BenchLM.
Compare top models on PostTrain Bench
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 2,000+ readers.
One email each week. Unsubscribe anytime.