Bittensor subnet's REAX 1, fine-tuned from Perplexity Decider, beats its base across all 10 areas
markjeffrey · x · 2026-10-23
REAX Labs released REAX 1, an open decision model on Bittensor subnet SN92, fine-tuned from Perplexity Decider v1.2. Self-reported tests show +2.4 points on average over the base, leading in all 10 areas (forecasting & risk +6.9) and all 6 draws; the demand-forecasting champion beat the s1-fast reference in 52 of 52 scored entries. An open competition started the same day — beat REAX 1, earn rewards, scoring on sealed items. Note: vendor's own measurements, not an official leaderboard.
Related event: REAX Labs Releases Open Decision Model REAX 1 with Mining Contest(2 posts)→
More from Models
- Artificial Analysis launches AA-PersonalityBench model personality benchmark — ArtificialAnlys · 2026-10-23
- OpenAI's Dot UX: Speech Is Linear, Real Value Is Multithreaded — cocktailpeanut · 2026-10-23
- Interpolation and hallucination: why sampling outside training data yields AI slop — gerardsans · 2026-10-23
- Sam Altman: models now find bugs outside any hacker threat model, 'we can't just patch them all' — ns123abc · 2026-10-23
- Omnii Genome: single generalist model beats AlphaGenome at linking variants to gene activity — BenSiranosian · 2026-10-23
- MemTensor ships MemT-1.0 nano and flash with a new parametric memory design — Alarming-Ad8154 · 2026-10-23