HALO-Gemini-3-Flash-AppWorld
- Type
- dataset
- Venue
- inference-net
- Year
- 2026
- Source
- huggingface
- Access
- free
- Language
- en
- Added
- 2026-07-17T20:02:14.335355+00:00
- Verified
- 2026-07-17T20:02:14.335355+00:00
Summary
This dataset contains agent execution traces of **Gemini 3 Flash** running on the [AppWorld](https://appworld.dev) benchmark, specifically evaluated on the **`test-normal`** dataset split. The traces capture the full span-level execution detail of the model interacting with AppWorld's simulated app ecosystem.
Keywords
hf-dataset language-modeling json text datasets pandas polars mlcroissant traces agent-traces appworld gemini halo rlm inference-net
Topics
Language Modeling
Research notes
- downloads=39; likes=7