ProgramBench gets run viewer: visualize agent performance per task, e.g., GPT-5.6 Sol xhigh

OfirPress · x · 2026-08-13

Ofir Press shares a run viewer built by @jyangballin for ProgramBench, allowing visualization of each agent's performance on every task. Example shows GPT-5.6 Sol xhigh achieving 1.3% tests passing on SQLite.

Original post →

More from coding & agent

coding & agent channel →