Traces

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

Cranelift Codegen Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1Muse Spark 1.20.0000$33.79127.0M205k10h 23m3565
2Muse Spark 1.20.0000$18.72115.3M194k3h 23m3504
3Muse Spark 1.20.0000$87.58303.3M711k10h 13m5625
4Muse Spark 1.20.0000$76.77223.4M655k10h 10m4507
5Muse Spark 1.20.0000$49.18242.6M532k8h 28m4959