NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-06-01J4MXXKZ0HJ0RCMC20PKZRF67
Run Details
Model:
GPT-4o, Aug. 6th (temp=1)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.3s
Cost:
$0.003118
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3935%
Overall
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
"Bill, you do realize we're stealing from a children's party, right?" "Molly, they're just sitting there, unguarded! Think of it as... a donation to us." "Donation? From toddlers?" "Sure! We're freeing them from the tyranny of abundance." "You mean cashmere sweaters and plastic trucks?" "Exactly! But we have to blend in. Party hats?" "You’d seriously wear a pointy hat for a few boxes of LEGO?" "It adds to the character, Molly! We’re festive heist professionals." "Okay, so what's the plan?" "We sneak in. You distract the talent, I'll grab the goods." "Distract the talent? Bill, the talent is a clown making balloon animals." "Precisely! I believe you have a history with clowns, don't you?" "Let it go. That was one slip-up." "One slip-up involving squeaky shoes and confetti." "Which you promised not to mention again." "Fine, fine. Just keep Bozo busy, and I'll handle the heavy lifting." "Heavy lifting? It's a birthday piñata, not Fort Knox!" "Don't underestimate the layers of paper-mâché. We go in light, come out rich." "And what if we get caught?" "We'll just say our gift was stolen first. It's foolproof!" "You're insane. But... okay, let's blend in and go pro." "That’s the spirit. Here’s a hat."
id
"gen-0nrZRmuBHrV27ucXTvxTbiWMfE0R"
total_cost
0.0031175
upstream_id
"chatcmpl-9tNEABmFmrEHBYBxNoQlnrgJknmKD"
created_at
"2024-08-06T22:45:58.204807+00:00"
8/6/2024, 10:45:58 PM
model
"openai/gpt-4o-2024-08-06"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4018
moderation_latency
196
generation_time
0
finish_reason
"stop"
tokens_prompt
68
tokens_completion
305
native_tokens_prompt
67
native_tokens_completion
295
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0031175
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
204
wordsDialogue
204
68.3935%