Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
Karpo released a family of six open-weight decision models from 0.8B to 31B, with the 31B variant scoring 73.9 to tie for first among 300 entries on the Decision Index. It replaces autoregressive decoding with a readout head that scores each option as a single token, producing zero generated tokens and always-valid answers, and beats Gemini Decision 1 on Amazon ESCI and New Yorker Caption.