跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.26829 · v2

ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry

首次提交 2026-10-20 01:55
版本更新 2026-11-18 10:39
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

ProteinGeoBench is a set of 131 tasks that give an agent protein structure files and ask it to look up recorded facts, check sequences, calculate geometry from atom coordinates or reason about structures. We ran four frontier models on every task several times (4,249 runs) and 26 models on a subset. A single overall score hides two different skills. Three of the four frontier models are best at looking up facts and worst at calculating from coordinates: Claude Opus 5 scores 0.907 on lookup and 0.716 on calculation. Gemini 3.1 Pro is the exception. Geometry is overrepresented among the hardest tasks. Half of the twelve tasks that all four models fail are calculations, although calculations are a fifth of the suite, and eight of the twelve were solved by none of the 26 models. The three leading models are within 0.031 of one another, too close to order, and with one run per task a different model ranks first in 24% of bootstrap resamples. Reports should therefore give scores by task type and the number of runs per task. They should also state the agent harness, the software that runs the model, and its network access, because both change scores. On a 15-task subset, blocking eight structural databases lowered scores, and removing network access lowered them more. Replacing our harness with each provider's own command-line agent moved scores by up to 0.09 in either direction. Across the 26 models, those that scored higher on the other tasks also scored higher on calculation.

作者备注:24 pages, 2 figures, 10 tables. Benchmark and tasks: https://github.com/Protege-AI/ProteinGeoBench

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 10:39 · 最新观测版本

ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in Geometry

ProteinGeoBench is a set of 131 tasks that give an agent protein structure files and ask it to look up recorded facts, check sequences, calculate geometry from atom coordinates or reason about structures. We ran four frontier models on every task several times (4,249 runs) and 26 models on a subset. A single overall score hides two different skills. Three of the four frontier models are best at looking up facts and worst at calculating from coordinates: Claude Opus 5 scores 0.907 on lookup and 0.716 on calculation. Gemini 3.1 Pro is the exception. Geometry is overrepresented among the hardest tasks. Half of the twelve tasks that all four models fail are calculations, although calculations are a fifth of the suite, and eight of the twelve were solved by none of the 26 models. The three leading models are within 0.031 of one another, too close to order, and with one run per task a different model ranks first in 24% of bootstrap resamples. Reports should therefore give scores by task type and the number of runs per task. They should also state the agent harness, the software that runs the model, and its network access, because both change scores. On a 15-task subset, blocking eight structural databases lowered scores, and removing network access lowered them more. Replacing our harness with each provider's own command-line agent moved scores by up to 0.09 in either direction. Across the 26 models, those that scored higher on the other tasks also scored higher on calculation.

查看此版本解读 →查看此版本原文 ↗