ToolFailBench C
AI benchmark
- Built by
- University of California UC Berkeley
- Tier
- C why
- Snapshot
What is ToolFailBench?
ToolFailBench measures tool-use failure modes of LLM agents (tool-skip, result-ignore, output fabrication, unnecessary tool use) across 1,000 tasks in finance, medicine, law, cybersecurity and real estate.
“a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate”
arxiv.org/abs/2607.04686v1 ↗“a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate”
arxiv.org/abs/2607.04686v1 ↗“a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate”
arxiv.org/abs/2607.04686v1 ↗“a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate”
arxiv.org/abs/2607.04686v1 ↗
Who built ToolFailBench
Led by University of California, Berkeley.
Paper: arxiv.org/abs/2607.04686v1 ↗
Tier C
Niche: a handful of models scored, or built by an RL vendor.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 14 models scored
- in curated RL directories (1 pt)
How we got to tier C
- Adoption: 14 models scored. Tier C.
- Not yet read on X.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where ToolFailBench sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-19 snapshot.