Model

GPT-4 Turbo

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-07-19-01J35SSBG4H205MH7XK4FVD4QM

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

AI
Molly whispered excitedly, "Bill, you sure the blueprints are correct? Feels crazy to hit a kiddie party." Bill chuckled, adjusting his oversized clown hat, "Yep, exact-amundo! The gift pile's right behind the magician’s curtain. Easy peasy." "And the kids?" "Distracted by the puppet show. We slide in during the grand puppet finale." Molly grinned, "Stage left, snag the loot, stage right, exit—like ghosts!" Bill high-fived her, "Like very sneaky, gift-loving ghosts. Ready to be Bozo and Bubbles?" "Just promise me we won’t actually have to perform." "Hah! No clowning around on the job, Molly. We're in and out." "So, we grab everything? Even the weirdly shaped packages?" "Everything. If it's wrapped, it's ours. Big haul means more choices for fenceable goods." "What about the bouncy castle? I’ve always wanted one." "Not the time for shopping, Molly." "Right, right... professional. Focus on the gifts." "Exactly. We hit at 3 PM sharp. Ready to make the great escape?" "Ready. Let's make this the best worst party ever!" Bill nodded, "For them or for us?" Laughing, Molly adjusted her fake nose, "For our bank accounts!"
id"gen-q0aoNjY9E3a1AodK7Z4Xe5GWVutA" 
total_cost0.00902
upstream_id"chatcmpl-9mjppJqwPA5iP8dw2qV4Qmt41MQIz" 
created_at"2024-07-19T15:29:32.200778+00:00" Friday, July 19th, 2024 at 3:29:32 PM GMT+00:00
model"openai/gpt-4-turbo" 
app_id182717
streamedfalse
cancelledfalse
provider_name"OpenAI" 
latency10334
moderation_latency220
generation_time0
finish_reason"stop" 
tokens_prompt68
tokens_completion278
native_tokens_prompt68
native_tokens_completion278
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.00902

Evaluation details

Result Evaluator Details Meta Data
60.2752% Matches word count n/a
neededCleanfalse
words185
99.2218% Dialogue to Total Word Ratio
Ratio: 87.03%, Deviation: 2.97%
neededCleanfalse
wordsTotal185
wordsDialogue161
79.7485%