ReproRepo: leaderboard
Reproducing research results from papers and released code is central to scientific progress. Existing works have introduced benchmarks to evaluate whether LLM agents can assist with reproducibility, but they are difficult to scale due to their reliance on substantial manual effort for data curation and evaluation. We introduce ReproRepo, a scalable framework for reproducibility evaluation that le
Metric: Issue Match EM@10 (self-reported). Source: benchmarklist.com. Saturation forecast: Around August 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 25.4 | #31 |
| 2 | Claude Opus 4.7 | 21.7 | #49 |
| 3 | DeepSeek V4 Pro | 19.3 | #102 |
| 4 | GPT-5.4 Mini | 13.4 | #212 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=reprorepo · How It Works · Data refreshed daily, snapshot 2026-10-20.