Tool use / function calling
StableToolBench
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
Superseded baseline#18 of 55 most-superseded · first seen Mar 12, 2024
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
2 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites StableToolBench as a baseline.
Most public benchmarks still overlook other enterprise-grade challenges, notably distinguishing among near-duplicate tools, proactively eliciting mandatory arguments, and detecting or preventing tool-call hallucinations, shortcomings our framework is expressly designed to remedy.
“StableToolBench emphasized stability and reproducibility through API simulation and caching mechanisms, highlighting evaluation brittleness in real API-dependent setups”
What to use instead
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.