RL Leaderboard

Experiment History

全提出の評価結果 (3 件)

DateUserModelMean RewardStdCompletionEp. Length
2026-06-10tenhouTQC_v2294.7±78.990%646
2026-06-10tenhouTQC_v1226.4±122.170%842
2026-06-10tenhouSAC_v1-110.5±0.10%63