NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-07-19-01J35T29SWCTCGZS3YH96R50EC
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 peered through the ornate gates, her eyes narrowing as she calculated the best route to the mountain of brightly wrapped presents. The garden was a riot of color, balloons bobbing gently in the breeze, and kids scampering about with sticky fingers and wide grins. Bill stood beside her, tapping his foot impatiently. “I still think this is a bad idea,” Bill muttered, scanning the chaotic scene. Molly grinned, her eyes twinkling with mischief. “Since when did you grow a conscience, Bill? It’s a kiddie party, not Fort Knox. We’ll be in and out, and they’ll never notice.” Bill sighed, glancing at the balloons nervously. "You know they're kids, right? Not, like, mini security guards." She stifled a laugh, giving him a nudge. "Relax, will you? Kids can be easily distracted. We just need a diversion. What about the puppet show?” Bill frowned, rubbing his chin. “The one on stage already? Too risky. We need something more... explosive.” Molly raised an eyebrow. “Not literally, I hope?” He smirked, shaking his head. “Nah. Just need a bit of chaos. Remember that time with the sprinklers?” Molly grinned. “Perfect. You take care of that. I’ll handle the loot.” “Deal,” Bill said, finally cracking a smile as they secured their plan.
id
"gen-U9AxwOaFtQUi6bt88QNfAYEIn4Ob"
total_cost
0.00479
upstream_id
"chatcmpl-9mjuZblSCcftmH7U84LD7kzgAjeJh"
created_at
"2024-07-19T15:34:23.166999+00:00"
Friday, July 19th, 2024 at 3:34:23 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
8048
moderation_latency
216
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
294
native_tokens_prompt
67
native_tokens_completion
297
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00479
Evaluation details
Result
Evaluator
Details
Meta Data
95.9868%
Matches word count
n/a
neededClean
false
words
208
0.0000%
Dialogue to Total Word Ratio
Ratio: 48.08%, Deviation: 38.08%
neededClean
false
wordsTotal
208
wordsDialogue
100
47.9934%