PostTrainBench leaderboard
As of 6 Nov 2026, the top score on PostTrainBench is 41.8% by Claude Fable 5 (Anthropic), ahead of GPT-5.6 Sol at 36.2%, across 12 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 9 Jun 2026). The agent must run a post-training pipeline on a small model and hit target metrics. PostTrainBench is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- Claude Fable 5 holds the top PostTrainBench score at 41.8% (Epoch AI Benchmarking Hub, 9 Jun 2026).
- GPT-5.6 Sol is second on PostTrainBench at 36.2% (Epoch AI Benchmarking Hub, 9 Jul 2026).
- PostTrainBench: Post-training a small model to a target, end to end (Epoch AI Benchmarking Hub).
- 12 model configurations have a published PostTrainBench result on BenchLeader (BenchLeader, 6 Nov 2026).
- PostTrainBench does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Post-training a small model to a target, end to end.
- Published by
- Epoch AI Benchmarking Hub
- Category
- Agents & tools
- Index weight
- Reference only
- Models
- 12
- Data as of
- 6 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
The agent must run a post-training pipeline on a small model and hit target metrics.
How it is scored
Average score, as published.
What to keep in mind
Very few models measured; a research-engineering task.
- 1Claude Fable 5 (max)41.8%
- 2GPT-5.6 Sol (max)36.2%
- 3Claude Opus 535.0%
- 4Claude Opus 4.8 (high)33.8%
- 5Claude Opus 4.8 (max)32.9%
- 6Kimi K332.0%
- 7GLM 5.2 (max)31.7%
- 8Claude Opus 4.7 (xhigh)28.6%
- 9GPT-5.5 (xhigh)27.2%
- 10Grok 4.5 (high)23.4%
- 11Gemini 3.1 Pro22.0%
- 12GPT-5.4 (high)19.0%
| # | ||||
|---|---|---|---|---|
| 1 |  Claude Fable 5max | 41.8% | 65.3 | 2026-06-09 |
| 2 |  GPT-5.6 Solmax | 36.2% | 65.4 | 2026-07-09 |
| 3 | Claude Opus 5 | 35.0% | 65.2 | 2026-07-24 |
| 4 | Claude Opus 4.8high | 33.8% | 60.6 | 2026-05-28 |
| 5 | Claude Opus 4.8max | 32.9% | 60.2 | 2026-05-28 |
| 6 |  Kimi K3open ↗ | 32.0% | 59.1 | 2026-07-16 |
| 7 |  GLM 5.2maxopen ↗ | 31.7% | 59.5 | 2026-06-16 |
| 8 | Claude Opus 4.7xhigh | 28.6% | 57.4 | 2026-04-16 |
| 9 | GPT-5.5xhigh | 27.2% | 64.3 | 2026-04-23 |
| 10 |  Grok 4.5high | 23.4% | 56.9 | 2026-07-08 |
| 11 |  Gemini 3.1 Pro | 22.0% | 60.5 | 2026-02-19 |
| 12 | GPT-5.4high | 19.0% | 58.8 | 2026-03-05 |
More agents & tools benchmarks · All LLM benchmarks
Related benchmarks
Top head-to-heads on PostTrainBench
Cite as: BenchLeader, “PostTrainBench leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/posttrainbench.
PostTrainBench: questions
- What does PostTrainBench measure?
- The agent must run a post-training pipeline on a small model and hit target metrics. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on PostTrainBench?
- As of 6 Nov 2026, the highest score on PostTrainBench is 41.8% by Claude Fable 5 (result dated 9 Jun 2026), ahead of GPT-5.6 Sol at 36.2%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
- Which AI model leads PostTrainBench?
- Claude Fable 5 leads PostTrainBench with 41.8% as of 6 Nov 2026 (result dated 9 Jun 2026), ahead of GPT-5.6 Sol at 36.2%.
- How many models have PostTrainBench results?
- 12 model configurations have a PostTrainBench result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
- Who runs PostTrainBench and how often is it updated?
- PostTrainBench is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does PostTrainBench count toward the BenchLeader Index?
- No. PostTrainBench is shown for reference but left out of the composite index.