reasoning benchmark
PostTrainBench Lite Leaderboard
PostTrainBench Lite evaluates whether an agent can design and execute a full post-training strategy for a pretrained base model under a constrained time budget.
Updated Sep 5, 2026
Models3
Model coverage3
MetricScore
EvidenceB
PostTrainBench Lite Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score51.50% | Percentile100.00% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score50.30% | Percentile50.00% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score29.60% | Percentile0.00% | Participants3 | EvidenceC | Evaluated |
PostTrainBench Lite Highlights
The leading models and scores on this benchmark.
PostTrainBench Lite Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PostTrainBench Lite
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is PostTrainBench Lite?
What PostTrainBench Lite measures and how its scores work.
PostTrainBench Lite is a reasoning benchmark for evaluating post-training strategy design and execution.
It measures the design and execution of data, prompts, an RL recipe, and an eval loop, scored as normalized mean reward over the improvement window.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PostTrainBench Lite
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PostTrainBench Lite.
Which model scores highest on PostTrainBench Lite?
GPT-5.6 Terra is currently ranked first with 51.50%.
What are the top three models on PostTrainBench Lite?
The current leaders are GPT-5.6 Terra (51.50%), GPT-5.6 Sol (50.30%), and GPT-5.6 Luna (29.60%).
Which PostTrainBench Lite model has the lowest official input price?
GPT-5.6 Luna has the lowest matched official input price at $0.20 input / $1.2 output per 1M tokens.
Which models are fastest among PostTrainBench Lite results?
The fastest matched records are GPT-5.6 Terra (99.35 tok/s via OpenAI), GPT-5.6 Luna (41.87 tok/s via OpenAI), and GPT-5.6 Sol (2.36 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.