模型67
开源决策模型 Karpo-Decision-31B 发布,Decision Index 73.9 并列第一
原标题:A new open source decision model just launched, and it ranks first out of 300.
开源决策模型 Karpo-Decision-31B 发布,在 Decision Index 上以 73.9 与 GLiDE 27B 并列 300 个模型中的第一。
中文译文尚未完成,先为你展示原文。
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.
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 https://huggingface.co/MachinePulseAI/karpo-decision-31B 📝 Technical write-up https://karpo.ai/blog/karpo-decision-31b Here’s where I’d try it first: Search. Recommendations. Tool choice. Model routing. Browser actions. Point it at the slowest decision in your stack and tell us what breaks.查看原帖
