Traces

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

SGLang Inference System Optimization

task page →5 runs · indexed 2026-09-02
#ModelRewardCostIn tokOut tokTimeStepsSubmits
1GLM-5.30.0534$68.77241.2M448k15h 36m6508
2GLM-5.30.0211$67.37244.9M383k14h 17m69820
3GLM-5.30.0004$46.58170.2M369k10h 37m5917
4GLM-5.30.0000$50.83180.8M386k12h 52m5764
5GLM-5.30.0000$68.85206.5M390k14h 23m60717