reasoning benchmark
PostTrainBench
PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as AIME2025, BFCL, GPQA Main, GSM8K, and HumanEval.
Updated Aug 11, 2026
Models5
Model coverage5
MetricScore
EvidenceB
PostTrainBench Ranking
Higher score ranks better on this benchmark.
| 01 | MI | 37.1% | 100.0% | 5 | C | |
| 02 | MA | 36.6% | 75.0% | 5 | C | |
| 03 | ZA | 34.3% | 50.0% | 5 | C | |
| 04 | BY | 18.3% | 25.0% | 5 | C | |
| 05 | BY | 16.5% | 0.0% | 5 | C |
PostTrainBench Score Distribution
A closer view of the leading scores on this benchmark.
PostTrainBench Highlights
The leading models and scores on this benchmark.
What is PostTrainBench?
What PostTrainBench measures and how its scores work.
PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as AIME2025, BFCL, GPQA Main, GSM8K, and HumanEval.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PostTrainBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- posttrainbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PostTrainBench.
Which model scores highest on PostTrainBench?
MiniMax M3 is currently ranked first with 37.1%.
What does PostTrainBench measure?
PostTrainBench evaluates a model's ability to autonomously post-train base models. Given pretrain-only base models, the agent must complete the full pipeline of data synthesis, training, evaluation, and iteration within a time budget, scored across downstream benchmarks such as AIME2025, BFCL, GPQA Main, GSM8K, and HumanEval.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
5 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.