PulseAugur
中
实时 01:17:13
English(EN) I ran four decision models and five small LLMs on 6,662 decisions across six public datasets. Mammoth-1 led the average, but Qwen3.6 and Gemma 4 each reached 92

MAMMOTH-1在LLM决策模型测试中领先；Qwen3.6、Gemma 4在提示注入方面表现出色

作者 PulseAugur 编辑部 · [1 个来源] ·

对四个决策模型和五个小型大型语言模型（LLM）在6662个决策上的比较显示，MAMMOTH-1的平均表现最佳。然而，Qwen3.6和Gemma 4在提示注入任务上表现强劲，准确率均达到92.9%。研究人员已公开了测试工具和原始数据，并邀请对未来测试提出建议。 AI

影响 为小型LLM在决策制定和安全漏洞方面的比较性能提供了见解。

排序理由 LLM在决策任务和提示注入方面的性能比较。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

MAMMOTH-1在LLM决策模型测试中领先；Qwen3.6、Gemma 4在提示注入方面表现出色

本文如何被排名

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
LLM在决策任务和提示注入方面的性能比较。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · pournasserian ·

    我使用六个公开数据集上的 6,662 个决策，运行了四个决策模型和五个小型 LLM。Mammoth-1 平均领先，但 Qwen3.6 和 Gemma 4 各达到 92

    I ran four decision models and five small LLMs on 6,662 decisions across six public datasets. Mammoth-1 led the average, but Qwen3.6 and Gemma 4 each reached 92.9% on prompt injection. I published the harness and raw calls. Which task would you test next? # AI # LLM https:// pour…

    链接 pournasserian.com/…/decision-models-vs-sm…

相关实体

相关话题