Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Calling on WHEN2TOOL Medium
Loading...
-0.7
Delta Accuracy
Necessary (N)
-27.74
-20.72
-13.7
-6.68
May 10, 2026
Delta Accuracy
Delta Tool Calls
Delta Accuracy / -Delta Tool Calls
Updated 22d ago
Evaluation Results
Method
Method
Links
Delta Accuracy
Delta Tool Calls
Delta Accuracy / -Delta Tool Calls
Necessary (N)
model averaging=six mo...
2026.05
-0.7
-0.04
-17.9
PROBE&PREFILL
model averaging=six mo...
2026.05
-3.4
-0.54
-6.2
Sparse (S)
model averaging=six mo...
2026.05
-7.9
-0.47
-16.9
Necessary + Reason-then-Act
model averaging=six mo...
2026.05
-16.3
-0.82
-19.7
Sparse + Reason-then-Act
model averaging=six mo...
2026.05
-19.9
-1.04
-19.1
No Tool + Reason-then-Act
model averaging=six mo...
2026.05
-23.5
-1.12
-20.9
No Tool (X)
model averaging=six mo...
2026.05
-26.7
-0.72
-36.9
Feedback
Search any
task
Search any
task