NC Bench
Overview
About
Tests
Models
Model
GPT-4 Turbo
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35TDDZYCW8BXNZFG7GYRXED
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 crouched behind a stack of colorful party chairs, her eyes scanning the garden festooned with balloons and streamers. Beside her, Bill fiddled with a tiny walkie-talkie, camouflaged in a clown's oversized tie. "Bill, focus. We get in, we grab the loot, we get out. Kids' parties are chaotic—we blend in, no problem." Molly whispered, her gaze fixed on the stash of wrapped gifts piled under a giant, glittering banner reading 'Happy Birthday Tommy!' Bill nodded, adjusting his fake clown nose. "Right, right. But what if someone asks us to make balloon animals? I can only do worms." "Then today, we love worms," Molly retorted, rolling her eyes. "Stick to the plan. I'll handle the distractions, you handle the loot. Easy." "Are we really doing this?" Bill's voice wavered slightly. Molly shot him a look. "Yes, now let's move before they cut the cake. Once that happens, it's every thief for themselves." They shuffled towards the party, mingling with a group of unsuspecting parents. As Molly started a fierce debate over the best type of birthday cake to camouflage their true intent, Bill edged closer to the mountain of gifts, his heart beating wildly against his faux clown chest.
id
"gen-9UF6knJu1a3uxC6KHI0y2GxDAqNO"
total_cost
0.00893
upstream_id
"chatcmpl-9mk0RtSctFfcoIdXo472WHnKeMgVB"
created_at
"2024-07-19T15:40:30.147057+00:00"
Friday, July 19th, 2024 at 3:40:30 PM GMT+00:00
model
"openai/gpt-4-turbo"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
10359
moderation_latency
219
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
275
native_tokens_prompt
68
native_tokens_completion
275
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00893
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
41.2369%
Dialogue to Total Word Ratio
Ratio: 40.30%, Deviation: 9.70%
neededClean
false
wordsTotal
201
wordsDialogue
81
70.6179%