PROPEL C

Name: PROPEL
Creator: Vmax
Keywords: Coding,Long-Horizon

AI benchmark · Coding

Publisher: Vmax
Domains: Coding Long-Horizon
On X: @VmaxAI ↗
Tier: C why
Snapshot: October 11, 2026

Open benchmark ↗vmax.ai/research

Full listing name: PROPEL: Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier. Share of frontier-difficulty generated tasks roughly doubles across math, code and SWE.

Latest from Vmax on X

@VmaxAI ↗

Nethack is a really underrated benchmark
— VmaxAI (@VmaxAI) Sep 16, 2026
You should try Silico. Not only for mech interp, but for AI Research in general. Goodfire have put a lot work into building a great interface for long-horizon agent-driven research.
— VmaxAI (@VmaxAI) Aug 4, 2026
Following the blog post from our collaboration with @GoodfireAI, the arxiv paper for PROPEL is now available.
— VmaxAI (@VmaxAI) Jun 18, 2026

What is PROPEL?

PROPEL: Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier (arXiv:2606.18284, 2026-06-10; one Goodfire AI co-author). Share of frontier-difficulty generated tasks roughly doubles across math, code and SWE.

Tier C

Niche: a handful of models scored, or built by an RL vendor.

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.

built by Vmax
in curated RL directories (2 pts)

How we got to tier C

Adoption: built by Vmax. Tier C.
Not yet read on X.
In curated RL directories: 2 points, a floor of C.
Not yet confirmed by a line from its own site or paper.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Not on the map yet: no line from its own site or paper places it in a domain.

More Coding AI benchmarks

Coding RL environments

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.