NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=1)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXS5MDGQMYH71AH367BHXH
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
Messages
Meta
AI
"Are we really doing this, Bill?" "Absolutely, Molly! It's the perfect cover. Who'd suspect a couple of clowns at a kid's party?" "Clowns? You didn't say anything about wearing costumes." "Trust me, Molly. We blend in with big red noses and floppy shoes." "And how do we carry the loot with those?" "The noses will be fake, the loot bags are where the humor is." "What if we get caught?" "Who arrests clowns? Besides, we'll have wigs. No one will recognize us." "And what about the kids? We don't want to give them nightmares." "We just need fifteen minutes, in and out. Think of it as an educational magic trick." "Magic trick? Is that what we're calling theft these days?" "It's all in the presentation, Molly. Smoke and mirrors." "Do we even know what gifts they have?" "Billy's mom said LEGOs and video games. Enough motivation?" "Billy’s mom is a talker, huh? That makes things easier." "And don't forget cake watching as you exit. Adds authenticity." "Fine, but I draw the line at balloon animals." "No balloon animals. Just a quick snatch and dash." "You think this will really work?" "It’s in the bag, Molly. Trust in the plan, and my comedic genius." "Alright, Bill. Let’s paint our noses."
id
"gen-DunKsFW0X7vaYz43tikQF2kcEINp"
total_cost
0.0029775
upstream_id
"chatcmpl-9tNBolBqE1Jd4eHeXt0bZuSKDeoEt"
created_at
"2024-08-06T22:43:31.929879+00:00"
Tuesday, August 6th, 2024 at 10:43:31 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3490
moderation_latency
195
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
287
native_tokens_prompt
67
native_tokens_completion
281
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0029775
Evaluation details
Result
Evaluator
Details
Meta Data
93.6496%
Matches word count
n/a
neededClean
false
words
209
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
209
wordsDialogue
209
65.2188%