Traces

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

Notebook Compression

task page →5 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.30.2729$60.3265.3M317k6h 41m35711
2Muse Spark 1.30.2285$27.0179.4M314k19h 7m4078
3Muse Spark 1.30.2112$78.1476.4M260k11h 8m3583
4Muse Spark 1.30.1309$65.0467.7M249k11h 11m3716
5Muse Spark 1.30.1170$63.5077.9M313k5h 49m3263