All benchmarksprecision_at_10 (higher is better)
MTEB AppsRetrieval (default), precision_at_10
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 | 1.76 | Model card |
| 2 | granite-embedding-278m-multilingual ibm-granite · test | 0.97 | Model card |
| 3 | granite-embedding-107m-multilingual ibm-granite · test | 0.72 | Model card |
