Research Engineering Benchmark.

7 challenging open-ended ML research engineering tasks requiring multi-hour autonomous work. Agents compete against human researchers on real tasks like implementing new architectures or optimizing training pipelines. Score is normalized against human performance.

Best published scores.

5 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary

normalized-score · higher is better

2 steps
of state of the art.

Each row below marks a model that broke the previous record on normalized-score. Intermediate submissions are kept in the leaderboard above; only SOTA-setting entries are re-listed here.

Higher scores win. Each subsequent entry improved upon the previous best.

1. Nov 22, 2024o1OpenAI0.170
2. Apr 1, 2025o3OpenAI0.380

2 papers
tied to this benchmark.

Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies