Traces

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

Flight-Sim Renderer in OpenGL

task page →5 runs · indexed 2026-11-12
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Gemini 4 Hydrogen0.8653$108.63426.9M2.7M19h 39m9471
2Gemini 4 Hydrogen0.8650$93.65387.2M2.3M16h 19m8472
3Gemini 4 Hydrogen0.8151$106.85345.1M2.0M20h 0m8123
4Gemini 4 Hydrogen0.7834$92.21369.3M2.3M14h 23m8284
5Gemini 4 Hydrogen0.7762$72.04364.0M2.3M11h 17m8332