PostTrainBench v1.2 D
AI benchmark · Coding
What is PostTrainBench v1.2?
PostTrainBench v1.2 measures how well AI agents can post-train small base language models on one H100 GPU in 10 hours, scoring the resulting models across six weighted benchmarks.
Coding mostly
“Measuring how well AI agents can post-train language models”
posttrainbench.com/ ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
PostTrainBench earlier version
PostTrainBench v1.1 earlier version
Tier D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
On X · unclear, low buzz, from 3 posts about PostTrainBench v1.2 in the last month
The v1.2 release posts note a new leaderboard led by Fable 5.1, Harbor/Modal cloud support and evaluation fixes; there is little outside discussion.
How we got to tier D
- Adoption: no usage data. Tier D.
- On X: unclear, low buzz. “The v1.2 release posts note a new leaderboard led by Fable 5.1, Harbor/Modal cloud support and evaluation fixes; there is little outside discussion.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where PostTrainBench v1.2 sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-29 snapshot.