Model

Mistral Nemo 12B Celeste

Test

Data extraction

Scenario

What's the color of the car?

Run ID

2024-08-06-01J4MXRWN492GBNCGHK0R78JHB

Model input

User/Human
What color is Sarah's car based on the following text? Only return the color, nothing else. John owns a blue car. Sarah's car is the same color as the sky on a clear day. Peter's car is red. The sky is not green on a clear day.

Model response

AI
Blue
id"gen-yqPkz1ADgGi6n3NnAYMtHE6boiYe" 
total_cost0.0001035
upstream_id"cmpl-024345b21c334e279cbafa70d2f62dbf" 
created_at"2024-08-06T22:43:19.462366+00:00" Tuesday, August 6th, 2024 at 10:43:19 PM GMT+00:00
model"nothingiisreal/mn-celeste-12b" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Infermatic" 
latency236
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt63
tokens_completion1
native_tokens_prompt67
native_tokens_completion2
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0001035

Evaluation details

Result Evaluator Details Meta Data
Pass Matches text
Case insensitive: blue
 n/a
Pass Matches Regex
/\bblue\b/i
 n/a
100.0000%