Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

R2

Benchmarks

Task NameDataset NameSOTA ResultTrend
Rebuttal Quality EvaluationR2 (test)
Rigor (C)9.39
45
Simulation PerformanceR2
Accuracy46
26
Topological LocalizationR2 Ref. Sequence 3
Precision@1100
24
Topological LocalizationR2 Ref. Sequence 2
Precision@192
24
Topological LocalizationR2 Ref. Sequence 1
Precision@10.93
24
Topological LocalizationR2 Ref. Sequence 0
Precision@198
24
Code RepairR2
ASR6.77
3
Explanation GenerationR2
SFT (Mean Feature KL)0.1177
2
3D ATF reconstructionR2 (test)
LSD (0-20 / 312 Hz)0.78
1
Robot arm manipulationR2 Unseen v1 (test)
Metric-
0
Robot arm manipulationR2 Seen v1 (test)
Metric-
0
Showing 11 of 11 rows