Test summary
Prompt
48 Tools Run v10
Dataset
mcp-toolcall-acc
Status
15 Completed
Test run duration
11 minutes 49 seconds
Evaluation cost
-
Started At.
Jun 3, 2025, 2:24:11 PM
Author
M
Madhu Shantan
Summary by evaluator
Tool Call Accuracy
Result
Mean score
Pass rate
Fail
0.67
66.67%
Tokens
Type
Value
Total tokens
1073298
Input tokens
1054970
Completion tokens
18328
Cost
Type
Value
Total cost
$ 17.19915
Input token cost
$ 15.82455
Completion token cost
$ 1.3746
Latency (ms)
Type
Value
min
7897.00 ms
max
159776.44 ms
p50
34975.00 ms
p90
99007.00 ms
p95
159871.00 ms
p99
159871.00 ms
mean
45469.20 ms
stdDeviation
37979.2003
total
15