Test summary

HTTP Endpoint
Medical Assistant
Dataset
medical_assistant_eval_dataset
Status
10 Completed
Test run duration
3 minutes 1 second
Evaluation cost
$0.1395750
Started At.
Apr 29, 2025, 7:52:15 PM
Author
UUtsav Khandelwal

Summary by evaluator

Clarity
Output Relevance
Vertex Question Answering Helpfulness
Vertex Question Answering Relevance
Semantic Similarity
Correctness
ResultMean scorePass rate
Pass
1100%
Pass
0.8890%
Fail
0.7670%
Pass
0.8480%
Fail
0.650
Pass
-90%

Latency (ms)

TypeValue
min22468.00 ms
max114580.52 ms
p5064415.00 ms
p90 106815.00 ms
p95 114623.00 ms
p99 114623.00 ms
mean 72314.40 ms
stdDeviation29582.9551
total10