NC Bench
Overview
About
Tests
Models
Model
GPT-4o, Aug. 6th (temp=0)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-06-01J4MXVBNZ5NJZ1GCTF8RSN489
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
"Alright, Bill, what's the plan for the party heist?" "Molly, it's simple. We sneak in dressed as clowns." "Clowns? Really? You think that'll work?" "Absolutely. Who questions clowns at a kids' party?" "Fair point. But what about the presents? How do we grab them?" "Easy. We distract the kids with balloon animals." "Balloon animals? You know how to make those?" "Of course not. But I can fake it long enough." "And while you're faking it, I swipe the gifts?" "Exactly. You stuff them in the big clown bag." "Won't the parents notice a giant bag of presents walking out?" "Not if we time it with the cake cutting. Everyone loves cake." "Okay, but what if they ask us to perform?" "Then we juggle. You can juggle, right?" "Three balls, tops. What if they want more?" "Then we improvise. Throw in a few pies." "Pies? Where are we getting pies?" "From the kitchen. Every party has pies." "Alright, Bill, but what if the kids start crying?" "Then we make a quick exit. Clowns are supposed to be mysterious." "Mysterious or not, this better work." "Trust me, Molly. By the end, we'll be the life of the party." "And the owners of a lot of presents."
id
"gen-4MTZe5YWuhCCDKpc3InE46LXjO2k"
total_cost
0.0030775
upstream_id
"chatcmpl-9tNCy9eX8gGzHmwu9nlqDqb7GxERr"
created_at
"2024-08-06T22:44:43.949084+00:00"
Tuesday, August 6th, 2024 at 10:44:43 PM GMT+00:00
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
3707
moderation_latency
272
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
294
native_tokens_prompt
67
native_tokens_completion
291
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0030775
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
204
wordsDialogue
204
68.2661%