Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Procedure Planning on CrossTask T=3
Loading...
40.45
Success Rate (SR)
MTID
6.754
15.502
24.25
32.998
May 4, 2022
Dec 23, 2022
Aug 13, 2023
Apr 3, 2024
Nov 22, 2024
Jul 13, 2025
Mar 4, 2026
Success Rate (SR)
Mean Accuracy (mAcc)
Mean IoU (mIoU)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Mean Accuracy (mAcc)
Mean IoU (mIoU)
MTID
Horizon=3, Params (M)=...
2026.03
40.45
67.19
69.17
ViterbiPlanNet
Horizon=3, Params (M)=...
2026.03
39.75
67.39
76.92
P3IV
Protocol=Protocol 2
2022.05
24.4
-
-
P3IV
Protocol=Protocol 1
2022.05
23.34
-
-
PlaTe
2022.05
18.5
-
-
DDN
2022.05
12.18
-
-
Retrieval-Based
2022.05
8.05
-
-
Feedback
Search any
task
Search any
task