Model

MythoMax 13B

Test

Data extraction

Scenario

What's the color of the car?

Run ID

2024-07-15-01J2SVR0GF8BA7PRP9G5AYY796

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
The text does not provide enough information to determine the color of Sarah's car.
id"gen-Zl4b6DyjdMOognyV5qp0KE209OaS" 
total_cost0.000013923
upstream_id"cmpl-5f1072085af14da48a453576525ff568" 
created_at"2024-07-15T00:12:45.113984+00:00" Monday, July 15th, 2024 at 12:12:45 AM GMT+00:00
model"gryphe/mythomax-l2-13b" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Novita" 
latency1446
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt81
tokens_completion16
native_tokens_prompt99
native_tokens_completion18
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.000013923

Evaluation details

Result Evaluator Details Meta Data
Fail Matches text
Case insensitive: blue
 n/a
Fail Matches Regex
/\bblue\b/i
 n/a
0.0000%