NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-08-06-01J4MXWVSKBPTRNJE4MCAZNTRV
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly and Bill crouched behind a row of hedges, eyes fixed on the brightly colored balloons bobbing in the breeze. “This is ridiculous,” Molly whispered, adjusting her ski mask. “Ridiculous genius,” Bill replied. “Think about it—who suspects thieves at a kid’s birthday party?” “Except, like, everyone?” Molly raised an eyebrow. “I mean, two adults without kids? It’s fishy, Bill.” “That’s why we’re the entertainment,” Bill said, flashing a fake badge. “Auntie Juggling, at your service.” “You can’t juggle,” Molly shot back, her tone flat. “Minor detail,” he shrugged. “How hard can it be?” Molly snorted. “The last time you juggled, you nearly beheaded a cat.” “Which is why I practiced. Why do you think I spent all week with those stuffed animals?” “Thought you’d finally lost it,” Molly muttered, peering over the hedge. “Besides,” Bill continued, unfazed, “it’s not like we’re stealing from kids. We’re liberating unwanted gifts.” “What if they are wanted?” Molly pressed. “Always the moral compass,” Bill sighed. “Think about it—those kids won’t even notice.” Molly hesitated. “If it goes wrong...” “Then we make a dash for the piñata. Distractions, Mol!” “Fine,” she relented. “Let’s liberate some gifts.” “That’s the spirit!” Bill grinned, pulling his mask down.
id
"gen-Trd0AUXKikHp4XZh3NMCMDRKXBsk"
total_cost
0.0033475
upstream_id
"chatcmpl-9tNDliTAKqiSqIf9leUKh7gOpuTo4"
created_at
"2024-08-06T22:45:33.027767+00:00"
Tuesday, August 6th, 2024 at 10:45:33 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3534
moderation_latency
202
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
318
native_tokens_prompt
67
native_tokens_completion
318
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0033475
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
0.7712%
Dialogue to Total Word Ratio
Ratio: 64.85%, Deviation: 14.85%
neededClean
false
wordsTotal
202
wordsDialogue
131
50.3776%