FrontierSWE (v1) B

Name: FrontierSWE (v1)
Creator: Proximal
Keywords: Coding,Long-Horizon,Private Codebases

AI benchmark · Coding

Publisher: Proximal
Domains: Coding Long-Horizon Private Codebases
On X: @proximalhq ↗
Tier: B why
Snapshot: October 11, 2026

Open benchmark ↗proximal.ai/blog/frontierswe/

Full listing name: FrontierSWE (v1): 17 tasks, 20-hour budgets. https://www.proximal.ai/blog/frontierswe/ ; https://github.com/Proximal-Labs/frontier-swe

Latest from Proximal on X

@proximalhq ↗

At Proximal, we believe that building our own research infrastructure is crucial to design the highest-quality training data Today, we are sharing more information about our internal post-training stack
— proximalhq (@proximalhq) Oct 8, 2026
We have added Claude Haiku 5.5 and Sonnet 5.5 to the FrontierSWE leaderboard. Both models are extremely capable despite being smaller than Anthropic's flagship models Opus and Fable - Haiku outperforms GPT-5.6 Sol, GLM-5.3 and other strong models!
— proximalhq (@proximalhq) Oct 7, 2026
Many cybersecurity evals use differential execution to test whether agents can reproduce known software vulnerabilities Without added constraints, this creates fairness issues: Our evaluation shows that CyberGym is effectively saturated on a verified task subset
— proximalhq (@proximalhq) Oct 1, 2026

What is FrontierSWE (v1)?

FrontierSWE measures how well coding agents handle ultra-long-horizon, open-ended software engineering tasks in implementation, performance engineering and ML research, with 20-hour budgets and partial-credit scoring.

Coding mostly
“FrontierSWE is an ultra long-horizon coding agent benchmark that tests implementation, performance eng and ML research”
github.com/Proximal-Labs/frontier-swe ↗

Who built FrontierSWE (v1)

Proximal built it
“FrontierSWE is developed by the Proximal team in collaboration with external collaborators from academia and industry.”
proximal.ai/blog/frontierswe/ ↗

Tier B

Established: 15 or more models scored, or curated RL directories rate it.

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.

21 models scored
built by Proximal
in curated RL directories (7 pts)

How we got to tier B

Adoption: 21 models scored; built by Proximal. Tier B.
Not yet read on X.
In curated RL directories: 7 points, a floor of B.
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.

Where FrontierSWE (v1) sits

Its realm in the universe, live. Hover a star for its name; click to open it. Open it in the universe

The galaxy could not load. See every vendor on the board.

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.