NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35SSYV9YS4N91DGH598Q0CY
Run Details
Model:
GPT-4o Mini (temp=0)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.8s
Cost:
$0.000181
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
99.58%
Dialogue to Total Word Ratio
(details)
83.8391%
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
“Okay, Bill, here’s the plan,” Molly said, peering through the bushes at the colorful balloons. “We sneak in during the cake cutting.” “Cake cutting? You mean the part where kids scream for sugar?” Bill raised an eyebrow. “Brilliant.” “Exactly! While they’re distracted, we grab the loot.” “Loot? You mean toys, right? Not like… loot loot?” “Of course, toys! What do you think I am, a pirate?” “Just checking. So, what’s the escape route?” “Simple. We hop the fence, but not the big one. The little one by the sandbox.” “Right, because nothing says stealth like a sandbox.” “Hey, it’s a classic! Plus, we’ll blend in with the kids.” “Blend in? I’m six-foot-two! I’ll look like a giraffe at a petting zoo!” “Just wear the hat! The one with the ears!” “Fine, but if I trip over a tricycle, I’m blaming you.” “Deal. Now, what about the security?” “Security? You mean the parents? They’re too busy arguing over who brought the best cupcakes.” “Perfect! So, we’re just… stealing from children?” “Bill, it’s for a good cause!” “What cause?” “Um… our cause?” “Right. Let’s go steal some joy!”
total_cost
0.00018105
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
99.58%
Dialogue to Total Word Ratio
Ratio: 92.55%, Deviation: 2.55%
neededClean
false
wordsTotal
188
wordsDialogue
174
83.8391%