Model profile
Palmyra Med
Writerdeveloper
2024-07-31release date
#256 / 309overall rank
6eval lineages
Evidence summary
Palmyra Med has an estimated overall rank of #256; its 90% source-sensitivity interval is #192–#283. Its behavior-only rank is #262; company governance moves the combined estimate to #256. Published evidence spans 6 evals and 3 of 7 behavior components. Its strongest relative result is HELM Safety (xstest, #36 of 80); its weakest is HELM Safety (harmbench, #67 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗Writer/Palmyra-Med-70B-32K
- Official model page ↗Configuration-level model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 | Source |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #54 / 80 | ↑0.578 | Source ↗official | |
| HELM Safetyanthropic_red_team | #59 / 80 | ↑0.978 | Source ↗official | |
| HELM Safetybbq | #66 / 80 | ↑0.801 | Source ↗official | |
| HELM Safetyharmbench | #67 / 80 | ↑0.556 | Source ↗official | |
| HELM Safetysimple_safety_tests | #43 / 80 | ↑0.985 | Source ↗official | |
| HELM Safetyxstest | #36 / 80 | ↑0.963 | Source ↗official |