All benchmarksrecall_at_5 (higher is better)
MTEB AppsRetrieval (default), recall_at_5
As the model cards publish them, each model’s best result. Facthory has not run them; results are self-reported unless the hub verified them.
| # | Model | Result | Source |
|---|---|---|---|
| 1 | granite-embedding-125m-english ibm-granite · test | 13.89 | Model card |
| 2 | granite-embedding-278m-multilingual ibm-granite · test | 7.62 | Model card |
| 3 | granite-embedding-107m-multilingual ibm-granite · test | 5.42 | Model card |
