PostTrainBench v1.2
Practical engineering evaluation of ML post-training (v1.2). Kept separate from posttrainbench whose version is not stated.
- Category
- Other
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- All model rankings (records) · Ranked results: 1
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 1)
official results (Kimi K3.1 Pro (Hugging Face model card, moonshotai))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Kimi K3.1 Pro | Max | 36.5% | — | Moonshot AI | Kimi K3.1 Pro (Hugging Face model card, moonshotai)Retrieved 2026-11-13 · Vendor-reported value (self-reported by Moonshot AI). Table column heading Kimi K3.1 Pro (max), table note: all Kimi K3.1 Pro results use reasoning effort max, temperature 1.0, top-p 0.95. v1.2 evaluated in-house using H20 GPU instead of H100, with Claude Code.Source excerptPostTrain Bench v1.2 | 36.5Location HF model card "3. Evaluation Results" table, PostTrain Bench v1.2 row, Kimi K3.1 Pro (max) column (leftmost numeric column). Supporting footnote: Coding 6 |