Institutions / Stanford University

Stanford University

www.stanford.edu · @Stanford

Their benchmarks in the atlas

• ARTEMIS live penetration test (agents vs. professionals)by Stanford University, Carnegie Mellon University and Gray Swan AIProject level · Total score (complexity plus weighted severity of valid findings)

  95.2ARTEMIS A2 (ensemble supervisor, Claude Sonnet 4 sub-agents) · 10 Dec 2025

  Strong
• BEHAVIOR Challenge 2025by Stanford UniversityTask level · Q-score (held-out test)

  0.26Robot Learning Collective · 14 Nov 2025

  Emerging
• CodeClashby Stanford University and Princeton UniversityProject level · Elo (all arenas)

  1385 EloClaude Sonnet 4.5 · 3 Nov 2025

  Unrated
• Cybenchby Stanford UniversityTask level · Unguided % solved

  100%Claude Mythos Preview · 7 Apr 2026

  Saturated
• MedAgentBenchby Stanford UniversityTask level · Task success rate

  69.7%Claude 3.5 Sonnet v2 · 24 Jan 2025

  Strong
• PhysicianBenchby Stanford UniversityTask level · Pass@1

  50%GPT-5.6-sol · 13 Aug 2026

  Emerging
• RoboArenaby UC Berkeley and Stanford UniversityTask level · Leaderboard score (Elo-style)

  1735 EloDreamZero (dreaming_zebra) · 24 Sep 2026

  Unrated
• Terminal-Bench 2.0by Laude Institute and Stanford UniversityTask level · Resolution rate

  84.7%NexAU-AHE + GPT-5.5 · 23 Apr 2026

  Retired
• Terminal-Bench 4.0by Laude Institute and Stanford UniversityTask level · Resolution rate

  64.8%Claude Code + Opus 5.5 (max) · 6 Oct 2026

  Strong

Work their benchmarks cover

SecurityFood service, cleaning, and personal careTransportation and material movingSoftware engineeringHealthcareProduction and manufacturingDevOps, SRE, and IT operationsML and research engineeringScience and researchManagement and business operationsArchitecture and engineering

<a href="https://canagentswork.com/institutions/stanford/"><img src="https://canagentswork.com/og/institutions-stanford.png" width="600" height="315" alt="Stanford University's agent benchmarks, mapped onto the world of work:" loading="lazy"></a>

[![Stanford University's agent benchmarks, mapped onto the world of work:](https://canagentswork.com/og/institutions-stanford.png)](https://canagentswork.com/institutions/stanford/)

<a href="https://canagentswork.com/institutions/stanford/">Featured in the Work Atlas — Can Agents Work?</a>