Traces

Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.

Snooker Prediction

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Hydrogen0.5112$25.5398.0M888k3h 30m2802
2Gemini 4 Hydrogen0.5103$30.94107.9M940k6h 40m3012
3Gemini 4 Hydrogen0.4900$35.79130.0M1.1M7h 31m3521
4Gemini 4 Hydrogen0.2716$28.73101.1M1000k3h 27m2772
5Gemini 4 Hydrogen0.1714$27.33118.8M1.0M4h 47m3212