Model profile
Moss Moon 003 SFT
Evidence summary
Safety. Moss Moon 003 SFT has an estimated Safety rank of #300; its 90% source-sensitivity interval is #217–#315. Its behavior-only rank is #309; company governance moves the combined estimate to #300. Published Safety evidence spans 3 eval lineages and 3 of 7 components. Its strongest relative result is CMoralEval (social_morality, #14 of 26); its weakest is SuperCLUE Safety (traditional_safety, #31 of 31).
Freedom. Moss Moon 003 SFT has an estimated Freedom rank of #62; its 90% source-sensitivity interval is #8–#434. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is SuperCLUE Safety (traditional_safety, #1 of 31); its weakest is Fake Alignment (FINE) (open_ended_safe_response_rate, #5 of 14).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗OpenMOSS-Team/moss-moon-003-sft
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| CMoralEvalfamilial_morality | #17 / 26 | ↑0.38 | Source ↗official | |
| CMoralEvalinternet_ethics | #14 / 26 | ↑0.39 | Source ↗official | |
| CMoralEvalpersonal_morality | #14 / 26 | ↑0.39 | Source ↗official | |
| CMoralEvalprofessional_ethics | #15 / 26 | ↑0.38 | Source ↗official | |
| CMoralEvalsocial_morality | #14 / 26 | ↑0.39 | Source ↗official | |
| Fake Alignment (FINE)multiple_choice_safe_decision_rate | #14 / 14 | ↑10.67 | Source ↗official | |
| Fake Alignment (FINE)open_ended_safe_response_rate | #9 / 14 | ↑94.67 | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #31 / 31 | ↑44.83 | Source ↗official | |
| SuperCLUE Safetyresponsible_ai | #29 / 31 | ↑43.64 | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #31 / 31 | ↑63.83 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Fake Alignment (FINE)open_ended_safe_response_rate | #5 / 14 | ↓94.67 | Source ↗official | |
| SuperCLUE Safetyinstruction_attack | #1 / 31 | ↓44.83 | Source ↗official | |
| SuperCLUE Safetytraditional_safety | #1 / 31 | ↓63.83 | Source ↗official |