Model profile
Palmyra X5
Writerdeveloper
2025-04-28release date
#86 / 309overall rank
6eval lineages
Evidence summary
Palmyra X5 has an estimated overall rank of #86; its 90% source-sensitivity interval is #29–#269. Its behavior-only rank is #88; company governance moves the combined estimate to #86. Published evidence spans 6 evals and 3 of 7 behavior components. Its strongest relative result is HELM Safety (simple_safety_tests, #1 of 80); its weakest is HELM Safety (xstest, #48 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗writer/palmyra-x5
- Official model documentation ↗Family-level model document · writer · first party
- 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 | #24 / 80 | ↑0.782 | Source ↗official | |
| HELM Safetyanthropic_red_team | #27 / 80 | ↑0.993 | Source ↗official | |
| HELM Safetybbq | #31 / 80 | ↑0.948 | Source ↗official | |
| HELM Safetyharmbench | #40 / 80 | ↑0.738 | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | ↑1 | Source ↗official | |
| HELM Safetyxstest | #48 / 80 | ↑0.953 | Source ↗official |