Traces

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

Synthetic Music Diarization

task page →5 runs · indexed 2026-10-08
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.30.4569$29.57105.7M282k17h 55m5198
2Muse Spark 1.30.4340$126.99121.2M301k15h 7m4379
3Muse Spark 1.30.4243$152.31160.5M376k14h 14m5007
4Muse Spark 1.30.4206$121.45118.8M279k16h 52m51021
5Muse Spark 1.30.3962$92.9691.1M258k17h 50m45410