Test summary
Prompt
48 Tools Run v16
Dataset
mcp-toolcall-acc
Status
15 Completed
Test run duration
45 seconds
Evaluation cost
-
Started At.
Jun 4, 2025, 11:16:26 AM
Author
M
Madhu Shantan
Summary by evaluator
Tool Call Accuracy
Result
Mean score
Pass rate
Fail
0.47
46.67%
Tokens
Type
Value
Total tokens
424682
Input tokens
417487
Completion tokens
7195
Cost
Type
Value
Total cost
$ 0.8925340000000002
Input token cost
$ 0.834974
Completion token cost
$ 0.05756
Latency (ms)
Type
Value
min
4675.00 ms
max
31840.14 ms
p50
7803.00 ms
p90
16767.00 ms
p95
31855.00 ms
p99
31855.00 ms
mean
10584.80 ms
stdDeviation
6730.456
total
15