Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Open-ended instruction-following on SuperNI
Loading...
48.12
Average Accuracy
GRID
43.4712
44.6781
45.885
47.0919
Jul 19, 2025
Average Accuracy
BWT
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
BWT
GRID
Task Order=O2
2025.07
48.12
-31.2
SHLPT
Task Order=O2
2025.07
46.97
-33.97
GRID
Task Order=O1
2025.07
46.54
-31.15
SHLPT
Task Order=O1
2025.07
44.97
-32.2
ProgPrompt
Task Order=O2
2025.07
43.98
-41.65
ProgPrompt
Task Order=O1
2025.07
43.65
-37.27
Feedback
Search any
task
Search any
task