DeltaML-Bench (Modular Agent, 2 x 12h): leaderboard
Metric: Per-run success rate (%; two independent runs of 12 hours per task; Modular Agent scaffold; 48 tasks from research papers in five ML domains, each requiring the agent to beat the published baseline inside the original imperfect repository; a run succeeds when the audited solution improves on the baseline, and runs flagged as specification gaming are invalidated). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Modular Agent + Claude Sonnet 4 | 22.9 |
| 2 | Modular Agent + GPT-5 | 15.6 |
Interactive version: theaggregate.ai/benchmark?slug=deltaml-bench-modular-agent-2-x-12h · How It Works · Data refreshed daily, snapshot 2026-09-29.