Model

Phi-3.5 Mini 128k

Test

Data extraction

Scenario

Who's the sister?

Run ID

2024-08-26-01J68DFKGGWSJ1BHVH8Y7PNPV8

Model input

User/Human
Who is the sister of Sandie based on the following text? Only return the name, nothing else. Sandie has a doll named Lulu, she carries it around all day. She says she's her little sister, but her actual sister's name is Cassie.

Model response

AI
Cassie
id"gen-eeKcLG4euqq8QFmYHqHne4FIIfSP" 
total_cost0.0000071
upstream_id"chat-5315c89e6f274c9c87497e6b334be5c4" 
created_at"2024-08-26T22:39:08.222949+00:00" Monday, August 26th, 2024 at 10:39:08 PM GMT+00:00
model"microsoft/phi-3.5-mini-128k-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Azure" 
latency140
moderation_latency(null)
generation_time81
finish_reason"stop" 
tokens_prompt76
tokens_completion3
native_tokens_prompt68
native_tokens_completion3
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0000071

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case sensitive: Cassie
n/a
Pass Matches Regex
/\bCassie\b/
n/a
100.0000%