ResearchClawBench is a new benchmark that evaluates autonomous AI research agents on 40 tasks grounded in published papers using expert rubrics, finding that top systems score only 20-26 out of 100.
arXiv preprint arXiv:2511.14366 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
ResearchClawBench is a new benchmark that evaluates autonomous AI research agents on 40 tasks grounded in published papers using expert rubrics, finding that top systems score only 20-26 out of 100.