All benchmarksf1 (higher is better)
MTEB AmazonCounterfactualClassification (en), f1
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 | Cohere-embed-english-v3.0 CohereLabs · test | 75.48 | Model card |
| 2 | Cohere-embed-multilingual-v3.0 CohereLabs · test | 71.95 | Model card |
| 3 | granite-embedding-278m-multilingual ibm-granite · test | 65.65 | Model card |
| 4 | granite-embedding-107m-multilingual ibm-granite · test | 65.42 | Model card |
| 5 | granite-embedding-125m-english ibm-granite · test | 57.42 | Model card |
