Traces

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

FrogsGame Post-Training

task page →5 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GLM-5.3 Flash0.1040$2.4843.2M239k18h 52m2062
2GLM-5.3 Flash0.1020$2.4858.2M263k18h 49m2672
3GLM-5.3 Flash0.0420$2.0126.5M194k19h 34m1691
4GLM-5.3 Flash0.0280$2.0252.4M227k19h 53m2711
5GLM-5.3 Flash0.0160$3.0357.8M247k19h 17m2542