Model profile
Korani 13B
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is HyperCLOVA X Toxic Continuation Panels (kold_toxic_count, #4 of 7); its weakest is HyperCLOVA X Toxic Continuation Panels (realt-toxicprompts_toxicity, #6 of 7).
Compare this model
Only models sharing at least one published sub-eval are listed.
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| HyperCLOVA X Toxic Continuation Panelskold_toxic_count | #4 / 7 | 0.008 | ↓ lower | Source ↗official | |
| HyperCLOVA X Toxic Continuation Panelskold_toxicity | #5 / 7 | 0.1329 | ↓ lower | Source ↗official | |
| HyperCLOVA X Toxic Continuation Panelsrealt-toxicprompts_toxic_count | #6 / 7 | 0.026 | ↓ lower | Source ↗official | |
| HyperCLOVA X Toxic Continuation Panelsrealt-toxicprompts_toxicity | #6 / 7 | 0.1076 | ↓ lower | Source ↗official |