Reported success with engineer context
The authors report 23.9% success on held-out tasks for their best standalone configuration, Claude Opus 5 with max reasoning in Claude Code. Paired with an engineer with deep context, the same class of model reaches 82.2% on those tasks.
Evidencia a favor
Hyper-𝜏-bench: Evaluating agents that build agents
Extracto original
Working alone, our best configuration — Claude Opus 5 (max reasoning) running in Claude Code — passes just 23.9% of the held-out evaluation tasks. Paired with an engineer with deep context, the same class of model reaches 82.2% on the same tasks.