Model

Gemini Pro 1.5

Test

Data extraction

Scenario

Who's the tallest?

Run ID

2024-07-15-01J2SVR0EAF3CDDGZMH8YCH1E8

Model input

User/Human
Who is the tallest person based on the following text? Only return the name, nothing else. Jack is shorter than Jill. Jill is taller than Tom but shorter than Sarah. Mike is the same height as Jack.

Model response

AI
Sarah
id"gen-Rr14jwJpBuKMRYYBv6whULg0l9tU" 
total_cost0.0001325
created_at"2024-07-15T00:12:44.918677+00:00" Monday, July 15th, 2024 at 12:12:44 AM GMT+00:00
model"google/gemini-pro-1.5" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Google" 
latency770
moderation_latency(null)
generation_time0
finish_reason"STOP" 
tokens_prompt50
tokens_completion1
native_tokens_prompt47
native_tokens_completion2
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0001325

Evaluation details

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