NC Bench
Overview
About
Tests
Models
Model
GPT-4o, May 13th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SMXEEKGHEQ0FV8C89EDTA
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 the bushes, peering through the gaps at the colorful chaos of the children's party. "Alright, Bill, what's the plan?" Molly whispered, adjusting her black beanie. "Simple," Bill replied, grinning. "We blend in, grab the presents, and get out. Easy peasy." "Blend in? We're adults, Bill. How do you propose we do that?" "Costumes, Molly. Costumes. I brought a couple of clown outfits." Molly raised an eyebrow. "Clowns? Really? You think that's going to work?" "Trust me, kids love clowns. We'll be the life of the party." "Fine, but if I get a pie in the face, you're paying for my dry cleaning." Bill chuckled. "Deal. Now, let's get changed." A few minutes later, they emerged from the bushes, dressed in oversized, colorful clown suits. "How do I look?" Molly asked, adjusting her red nose. "Like a million bucks," Bill said, giving her a thumbs up. "Ready?" "As I'll ever be." They sauntered into the party, immediately drawing the attention of the children. "Hey kids, who wants to see some magic?" Bill called out, pulling a deck of cards from his pocket. Molly leaned in. "While you distract them, I'll start gathering the presents." "Got it. Just be quick." Molly nodded and slipped away, leaving Bill to entertain the crowd.
id
"gen-F1Ay7MwjiGCRVKHd8EwlaVl9Pnq0"
total_cost
0.004925
upstream_id
"chatcmpl-9mjnUZh6oLPe296jJIKVTSTTeCQAe"
created_at
"2024-07-19T15:27:03.41369+00:00"
Friday, July 19th, 2024 at 3:27:03 PM GMT+00:00
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
6475
moderation_latency
749
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
314
native_tokens_prompt
67
native_tokens_completion
306
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.004925
Evaluation details
Result
Evaluator
Details
Meta Data
68.1022%
Matches word count
n/a
neededClean
false
words
214
98.0659%
Dialogue to Total Word Ratio
Ratio: 53.74%, Deviation: 3.74%
neededClean
false
wordsTotal
214
wordsDialogue
115
83.0841%