Large language models (LLMs) perform increasingly well on biology benchmarks, but it remains unclear whether they uplift novice users -- i.e., enable humans to perform better than with internet-only resources. This uncertainty is central to understanding both scientific acceleration and dual-use risk. We conducted a multi-model, multi-benchmark human uplift study comparing novices with LLM access versus internet-only access across eight biosecurity-relevant task sets. Participants worked on complex problems with ample time (up to 13 hours for the most involved tasks). We found that LLM access provided substantial uplift: novices with LLMs were 4.16 times more accurate than controls (95% CI [2.63, 6.87]). On four benchmarks with available expert baselines (internet-only), novices with LLMs outperformed experts on three of them. Perhaps surprisingly, standalone LLMs often exceeded LLM-assisted novices, indicating that users were not eliciting the strongest available contributions from the LLMs. Most participants (89.6%) reported little difficulty obtaining dual-use-relevant information despite safeguards. Overall, LLMs substantially uplift novices on biological tasks previously reserved for trained practitioners, underscoring the need for sustained, interactive uplift evaluations alongside traditional benchmarks.

翻译：大型语言模型（LLM）在生物学基准测试中表现日益优异，但其是否能够提升新手用户的能力——即帮助人类取得优于仅使用互联网资源的表现——仍不明确。这一不确定性对于理解科学加速与双重用途风险至关重要。我们开展了一项多模型、多基准的人类能力提升研究，比较了在八组与生物安全相关的任务中，使用LLM的新手与仅使用互联网资源的新手之间的表现。参与者在充足时间内（最复杂任务耗时长达13小时）处理复杂问题。研究发现，使用LLM能带来显著的能力提升：使用LLM的新手准确率是对照组的4.16倍（95%置信区间[2.63, 6.87]）。在四个具备专家基线（仅使用互联网）的基准测试中，使用LLM的新手在其中三项上超越了专家表现。可能令人意外的是，独立运行的LLM往往优于LLM辅助的新手，这表明用户未能充分激发LLM的最强潜力。尽管存在安全防护措施，大多数参与者（89.6%）报告获取双重用途相关信息时未遇明显困难。总体而言，LLM显著提升了新手在以往仅限专业人员的生物学任务中的表现，这强调需要在传统基准测试之外开展持续、交互式的能力提升评估。