NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-19-01J35SMSCCE9S7H8DGBRTWTDF5
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Alright, Bill, we've scoped the playground. Now, what's the plan?" "Molly, it's genius. We dress up as clowns." "Clowns? You want us to wear big red noses and floppy shoes?" "Exactly. No one suspects the clowns." "Fine. But how do we avoid the kids?" "Simple. We get them to like us first." "Like us? How on earth do we do that?" "Balloon animals. Kids love balloon animals." "Balloon animals? Bill, I can barely make a snake." "Then you’re in luck. Most kids can’t tell the difference." "Alright, but what about the parents?" "We distract them with… face painting!" "Face painting? I can’t draw a straight line!" "Doesn't matter. Smudge a few colors, call it modern art." "And the presents? When do we grab them?" "Here's the clever part. We offer to move the gifts for a game." "You think they’ll buy it?" "They're kids, Molly. They’ll fall for it." "Fine. But if anyone gets suspicious?" "We juggle! Creates chaos, everyone loves chaos." "Okay, I juggled a watermelon once, didn’t end well." "Then stick to the scarves. Light and safe." "Alright, Bill. Clowns, balloons, face paint, and juggling. We got this." "Exactly. Steal the show, steal the presents." "And if it goes wrong?" "Run. Fast." "Deal. Let’s suit up."
id
"gen-lPhbiO8DTply9Tzq8Cxccgja35cu"
total_cost
0.005075
upstream_id
"chatcmpl-9mjnQI53rhaLePY4iazetdmTEU1tE"
created_at
"2024-07-19T15:27:00.280346+00:00"
Friday, July 19th, 2024 at 3:27:00 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
7861
moderation_latency
286
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
323
native_tokens_prompt
67
native_tokens_completion
316
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.005075
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
208
wordsDialogue
208
66.3873%