Test summary

Prompt
48 Tools Run v15
Dataset
mcp-toolcall-acc
Status
15 Completed
Test run duration
13 minutes 40 seconds
Evaluation cost
-
Started At.
Jun 4, 2025, 10:08:00 AM
Author
MMadhu Shantan

Summary by evaluator

Tool Call Accuracy
ResultMean scorePass rate
Fail
0.6766.67%

Tokens

TypeValue
Total tokens1173313
Input tokens1157461
Completion tokens15852

Cost

TypeValue
Total cost$ 3.710163000000001
Input token cost$ 3.472383
Completion token cost$ 0.23778

Latency (ms)

TypeValue
min6650.00 ms
max53884.71 ms
p5024367.00 ms
p90 51103.00 ms
p95 53887.00 ms
p99 53887.00 ms
mean 27064.80 ms
stdDeviation15148.2078
total15