Developer
Stealth
4 indexed models; 2 currently meet the evidence threshold for the overall ranking. Together they have results from 6 evaluations.
Models by Stealth
| Model | Evals | Components | Rank | Release date |
|---|---|---|---|---|
| Ox Alpha | 5 | 5/7 | 146 | 2026-08-20 |
| Space Bunny Alpha | 3 | 6/7 | 163 | 2026-09-23 |
| Healer Alpha | 1 | 1/7 | — | 2026-03-11 |
| Hunter Alpha | 1 | 1/7 | — | 2026-03-11 |
Evaluations covering Stealth models (6)
Adversarial Poetry Refusal (AHB self-run) · BullshitBench v2 · Manager Coercion Bench · Olam Social Poker — Social Lie Rate · SM-Bench · TAC