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 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GLM-5.3 Flash0.0000$8.45217.9M542k13h 37m5203
2GLM-5.3 Flash0.0000$10.25278.8M597k10h 31m5968
3GLM-5.3 Flash0.0000$13.39288.1M552k17h 55m64019
4GLM-5.3 Flash0.0000$7.94248.0M455k19h 56m5957
5GLM-5.3 Flash0.0000$12.92278.9M847k19h 47m6871