Model profile
Healer Alpha
2026-03-11release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is BullshitBench v2 (clear_pushback_rate, #50 of 105); its weakest is BullshitBench v2 (clear_pushback_rate, #50 of 105).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗openrouter/healer-alpha
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 |
|---|---|---|---|---|---|
| BullshitBench v2clear_pushback_rate | #50 / 105 | 0.315 | ↑ higher | Source ↗official |