NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-05-22-01JVWHA5AZ2GCP475H079SWWFE
Run Details
Model:
Claude Opus 4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
20.4s
Cost:
$0.025350
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
Overall
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 peered through the binoculars at the bouncy castle in the backyard. "Target acquired. I count twenty-seven presents on the gift table." "Twenty-seven?" Bill squinted through his own pair. "I see twenty-eight. There's a tiny one behind the piñata." "That's a juice box, Bill." "Could be a gift card inside." Molly lowered her binoculars and sighed. "When I said we needed to think outside the box for our next score, this wasn't what I meant." "You said hit soft targets. What's softer than a bunch of six-year-olds?" Bill pulled out his tablet, showing a crude diagram. "Look, I've mapped out the entire operation. We go in disguised as clowns—" "Absolutely not." "—create a distraction with balloon animals, then make our move during pin-the-tail-on-the-donkey." "Bill, it's a kid's birthday party." "Exactly! Their security is terrible. Look, the mom just left the side gate wide open." "That's for guests." "We could be guests. Very late guests. With face paint." Molly watched a child face-plant into the cake. "You know what? Fine. But I'm not wearing the red nose." "Deal. I'll take the red nose. You get the oversized shoes."
total_cost
0.02535
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 70.35%, Deviation: 20.35%
neededClean
false
wordsTotal
199
wordsDialogue
140
40.6364%