Galileo
We track 6 benchmarks that Galileo made or helped make.
0 in use 3 with public code 4 with a leaderboard here
Benchmarks
| Name | Kind | Released | Best score | Status |
|---|---|---|---|---|
| Galileo Agent Leaderboard Models pick and call tools on samples drawn from existing tool-use benchmarks. Galileo scores Tool Selection Quality with an LLM judge and averages the datasets equally. | Function calling | Feb 2025 | 0.95 | Not in cards |
| Galileo Agent Leaderboard v2 Agents handle simulated multi-turn customer support conversations in banking, healthcare, insurance, investment and telecom, with synthetic personas and domain tools. Scores are Action Completion and Tool Selection Quality. | Customer service | Jul 2025 | 62% | Not in cards |
| Galileo LLM Hallucination Index Models answer questions with and without retrieved context and generate long responses. Galileo judges factual accuracy and adherence to the supplied context. | Hallucination rates | Nov 2023 | 0.79 | Not in cards |
| Galileo LLM Hallucination Index RAG Special Models answer questions using short, medium, and long passages. Galileo judges whether each answer follows the supplied context. | Faithful to sources | Jul 2024 | 0.99 | Not in cards |
| RAGBench Evaluators judge whether retrieved passages are relevant and generated answers are grounded. Galileo compares their judgments with reference annotations. | Faithful to sources | Jun 2024 | Not in cards | |
| RealHall Evaluators score model responses for hallucinations. Four datasets cover questions with and without reference documents. The score measures agreement with binary ground truth labels. | Hallucination rates | Oct 2023 | Not in cards |