CN
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CN rac-dist
888Mean Episodic Reward
21
CN rdist
-161Mean Episodic Reward
21
CN rdete
-154Mean Episodic Reward
21
CN
65Win Rate
9
CN (Medium)
35Backward Transfer
8
CN (Expert)
5.83Backward Transfer
8
CN Medium
16Forward Transfer
7
CN Expert
6.74Forward Transfer
7
CN MPE hard
3.37Mean Episode Reward
7
CN MPE medium
3.21Mean Episode Reward
7
CN15k
16.61P Score
6
CN (test)
28.3Runtime (s)
4
CN
55.2Accuracy
4
CN Ver. Dual
1,377.9Token Usage
3
CN (Single)
0.89Invocation Accuracy
3
Cn independent non-negative random variables
1Lower Bound Competitive Ratio
1
Cn independent non-negative random variables
2Lower Bound Competitive Ratio
1
Cn independent non-negative random variables
1Lower Bound Competitive Ratio
1
Cn independent non-negative random variables
1Lower Bound Competitive Ratio
1