Traces

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

Machine-Learned Interatomic Potential

task page →5 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Argon0.9973$144.92105.5M303k19h 54m27310
2Gemini 4 Argon0.9944$61.2455.2M244k20h 19m18914
3Gemini 4 Argon0.9938$60.3445.2M281k20h 31m16713
4Gemini 4 Argon0.9931$56.1857.5M250k20h 47m20910
5Gemini 4 Argon0.9823$48.4349.9M216k20h 21m19920