Leaderboard › Model
Benchmarks
Progress through an episode
Each band shows how many episodes of GPT-6 Astra, paused had succeeded, partly succeeded (some subtask score) or had no success at each second of simulated time. An episode that has ended stays in its band. The dashed line shows the mean Reliability, the mean subtask score.
Episodes
Each episode of GPT-6 Astra, paused on RoboLab-120, the newest first.