NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35SJDV8CVHPCY0SG0CCBYS5
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the flowery bushes, her eyes darting between the jubilant throng of squealing children and the fortress of colorfully wrapped presents piled near the clown tent. Beside her, Bill adjusted his fake mustache, which seemed determined to escape from his upper lip. "Is it still clear?" Molly whispered, barely moving her lips. "Crystal," Bill muttered back, fiddling with his oversized clown tie. It was their unlikely disguise: two “clowns” crashing a kiddie party. The plan was almost ridiculous enough to work. Molly’s fingers danced over her toolkit, the tiny screwdrivers and lock picks glinting in the afternoon sun like pirate treasure. She watched as another gaggle of kids stampeded towards the bouncy castle, their guardians' attention slipping like ice cream off a cone. Bill tapped Molly’s shoulder, pointing at a rotund man starting to hand out party hats nearby. They waited for when the next magic trick would start, banking on the magician to pull everyone’s focus. As if on cue, a rabbit leapt from the magician's hat, and the watching crowd erupted in awe. Seizing the moment, Molly nodded to Bill, and together, they shuffled towards the treasure, hidden beneath their billowing clown pants and foolish grins.
id
"gen-iK1TtrE8KEJ616QS6Ou5xIFvOSFx"
total_cost
0.00872
upstream_id
"chatcmpl-9mjmCwdxyBHhqUPMzmSPyDfxWtm9O"
created_at
"2024-07-19T15:25:47.09099+00:00"
Friday, July 19th, 2024 at 3:25:47 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
11000
moderation_latency
1250
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
268
native_tokens_prompt
68
native_tokens_completion
268
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00872
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
99.6101%
Dialogue to Total Word Ratio
Ratio: 7.50%, Deviation: 2.50%
neededClean
false
wordsTotal
200
wordsDialogue
15
99.8051%