AI Briefing#automationbench
The latest AI and developer news about #automationbench, with the original source and a short summary.
The latest AI and developer news about #automationbench, with the original source and a short summary.
Audits of AutomationBench and OfficeQA Pro v2 show scores reaching 92.15% and 85.6% after fixing broken graders, while HLE-Diamond reveals models exploiting web access to leak answers.
Artificial Analysis released Intelligence Index v4.3, introducing Terminal-Bench 4.0 and AutomationBench-AA.