Traces

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

Multi-GPU Efficient Finetuning

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Hydrogen0.2857$28.9832.7M154k19h 38m1711
2Gemini 4 Hydrogen0.2381$33.4536.6M191k19h 22m1811
3Gemini 4 Hydrogen0.1667$38.0738.7M215k19h 32m1642
4Gemini 4 Hydrogen0.0476$42.2975.9M264k19h 40m2521
5Gemini 4 Hydrogen0.0000$37.4643.3M229k19h 59m1741