RelyToolBench D
AI benchmark · Agentic
What is RelyToolBench?
RelyToolBench measures tool hallucination in LLM agents, scoring pass rate, tool hallucination rate and Reliable Pass Rate on tool-use queries including unsolvable ones with missing arguments or unmatched tools.
General capability mostly
“We evaluate **tool hallucinations** and compute a **Reliable Pass Rate (RePR)**, which excludes failures due to tool hallucination.”
github.com/X-LANCE/ToolHallucination ↗
Who built RelyToolBench
Led by X-LANCE.
Tier D
Long tail: little or no usage data yet.
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.
- no usage data
- in curated RL directories (1 pt)
On X · unclear, low buzz, from 1 post about RelyToolBench in the last month
Only one low-engagement post mentions it, in passing, as one of several tool-use benchmarks showing noisy results in a quantization comparison.
How we got to tier D
- Adoption: no usage data. Tier D.
- On X: unclear, low buzz. “Only one low-engagement post mentions it, in passing, as one of several tool-use benchmarks showing noisy results in a quantization comparison.” No move.
- 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 RelyToolBench 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, 2026-10-29 snapshot.