Maker-reported (not independently measured by JevMade): 8th place in text-only benchmark
- Primitives
- Not stated
- Added
Source checked 2026-09-25 — opened the primary source directly.
Benchmarks & research
XOR on Decision Index 0.2
Decision Index 0.2 places XOR eighth among Jev-like text models, with comparatively strong results in arts and human taste.
Screenshot unavailable. Open the experiment ↗