Open Source Karpo Decision Model Tops 300-Model Leaderboard

Original title: A new open source decision model just launched, and it ranks first out of 300.
78AI Score

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.

Full Report

Rohan Paul (@rohanpaul_ai) · 2026-11-17 19

A new open source decision model just launched, and it ranks first out of 300.

Karpo-Decision-31B swaps decoding for a readout head: a single-token code per option, one score per code, a softmax over that question's options. Zero generated tokens, always a valid answer, and the page is shared across questions through branch attention.

Decision Index Full: 73.9, the top score, tied #1 of 300 with GLiDE 27B at 73.4. The base is Gemma 4 31B, yet it beats Google's Gemini Decision 1 on Amazon ESCI, 64.7% vs 58.7%, and New Yorker Caption, 90.5% vs 79.7%.

Against Jev 1.14 it runs 95 ms vs 196 ms median, and JevBench estimates about a fifth less per 1,000 decisions.

Open weights matter for search and recommendation teams, who need many relevance calls per query, and for personal agents that need a calibrated act-or-ask threshold.

↳ 引用 @LeahW_2077 (LeahW): Picking the next tool shouldn’t take a paragraph.

We built Karpo Decision. A family of six open-weight models, from 0.8B to 31B.Give it the context, a question, and the options. It returns a probability for each option in one forward pass.

Karpo Decision 31B 🏆 73.9 on Decision Index, tied for #1 on the Nov 12 board ⚡ 94 ms median per request on a single RTX PRO 6000 📊 87.2 on JevBench Capability vs. 78.5 for Google’s Gemini Decision 1

🤗 Hugging Face

推文配图

推文配图