Traces

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

FFmpeg libswscale Optimization

task page →5 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GLM-5.3 Flash0.1268$16.00489.1M1.2M13h 53m1179110
2GLM-5.3 Flash0.0819$11.44312.2M1.0M11h 47m7862
3GLM-5.3 Flash0.0721$12.54348.2M1.1M9h 45m8384
4GLM-5.3 Flash0.0710$14.74418.0M1.0M13h 2m9636
5GLM-5.3 Flash0.0591$10.52294.6M1.1M15h 39m7681