SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers

arXiv '25 2025 36.6 benchmark

Read-first score

Read-first score 36.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals.

Recency 11%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 33%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=True; dataset=False; markers=github

Topical relevance 56%

4.8

Matches configured research keywords against title, abstract, tags, and analysis text. matched=1

FrontierReproducibility anchor

Stability: volatile; rank range: 81.