reasoning benchmark
PostTrainBench Leaderboard
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 17, 2026
Models6
Model coverage6
MetricScore
EvidenceB
PostTrainBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelZA | Score39.8% | Percentile100.0% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score37.1% | Percentile80.0% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score36.6% | Percentile60.0% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelZA | Score34.3% | Percentile40.0% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelBY | Score18.3% | Percentile20.0% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelBY | Score16.5% | Percentile0.0% | Participants6 | EvidenceC | Evaluated |
PostTrainBench Highlights
The leading models and scores on this benchmark.
PostTrainBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for PostTrainBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis posttrainbench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ZAGLM-5.3Zhipu AI
- Score
- 39.8%
Strengths
- Ranks #1 of 6 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures PostTrainBench, not total model capability
- 02MIMiniMax M3MiniMax
- Score
- 37.1%
- Price
- $0.30 input / $1.2 output per 1M tokens
- Speed
- Up to 214 tok/s via Together
Strengths
- Ranks #2 of 6 compared models
- 80th percentile on this benchmark
- C evidence result
Considerations
- This result measures PostTrainBench, not total model capability
- 03MAKimi K3Moonshot AI
- Score
- 36.6%
- Price
- $3.0 input / $15 output per 1M tokens
- Speed
- Up to 26 tok/s via Fireworks
Strengths
- Ranks #3 of 6 compared models
- 60th percentile on this benchmark
- C evidence result
Considerations
- This result measures PostTrainBench, not total model capability
- 04ZAGLM-5.2Zhipu AI
- Score
- 34.3%
- Price
- $1.4 input / $4.4 output per 1M tokens
Strengths
- Ranks #4 of 6 compared models
- 40th percentile on this benchmark
- C evidence result
Considerations
- This result measures PostTrainBench, not total model capability
- 05BYSeed 2.1 TurboByteDance
- Score
- 18.3%
Strengths
- Ranks #5 of 6 compared models
- 20th percentile on this benchmark
- C evidence result
Considerations
- This result measures PostTrainBench, not total model capability
Selection summary
Best AI Models for PostTrainBench
GLM-5.3 currently leads PostTrainBench with 39.8%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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?
GLM-5.3 is currently ranked first with 39.8%.
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?
6 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.