All benchmarksmain_score (higher is better)
MTEB AmazonCounterfactualClassification (en), main_score
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-278m-multilingual ibm-granite · test | 71.81 | Model card |
| 2 | granite-embedding-107m-multilingual ibm-granite · test | 71.67 | Model card |
| 3 | granite-embedding-125m-english ibm-granite · test | 63.4 | Model card |
