NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-04-16-01JRZZ8N0XQQWJAWRYRZ3GXNJS
Run Details
Model:
o4 Mini High
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 16s
Cost:
$0.030111
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
92.57%
Dialogue to Total Word Ratio
(details)
96.2858%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Crimson streamers dangled over a vinyl wall, humming faintly under a row of blinking battery lights. Molly perched on tiptoes, scanning the room through a dense barricade of balloons shaped like unicorns. Bill adjusted his oversized teddy suit head, nostrils flaring at the hint of vanilla frosting. A flicker of tinsel loomed in the distance, guarding a long table strewn with colorfully wrapped boxes. Soft giggles drifted through a slit in the door. They crouched behind a decorative piñata, sharing a conspiratorial smirk. Molly’s heart pounded like drumbeats in a fairy tale band. Bill’s gloved fingers trembled over a glitter bomb labeled ‘Celebrate Good Times.’ Outside, a distant shout announced the clown’s arrival. They exhaled silent breaths, shaking their heads at the absurdity of stealing birthday loot from pint-sized ballerinas and dinosaur enthusiasts. Yet the promise of hundreds of prank whistles and soap bubbles in their sacks was too tempting to resist. A door hinge creaked. Everything hinged on timing and a well-aimed swoop of neon confetti. They grinned like sugar-fiends at a candy buffet. Giggling with glee. Molly: "Check every corner. No one spots glitter tonight at midnight." Bill: "Operation Fiesta is in motion. Cake batter is lethal, seriously."
id
"gen-1744829699-cVKnbA5wZifmQkkqcF6q"
upstream_id
"chatcmpl-BN2CRCZHGZg0hlmY1Z2VIv8viQ8fn"
total_cost
0.0301114
cache_discount
(null)
provider_name
"OpenAI"
created_at
"2025-04-16T18:56:15.80283+00:00"
4/16/2025, 6:56:15 PM
model
"openai/o4-mini-high-2025-04-16"
app_id
182717
streamed
true
cancelled
false
latency
72439
moderation_latency
126
generation_time
75585
tokens_prompt
68
tokens_completion
6808
native_tokens_prompt
66
native_tokens_completion
6827
native_tokens_reasoning
6528
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0301114
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
92.57%
Dialogue to Total Word Ratio
Ratio: 15.27%, Deviation: 5.27%
neededClean
false
wordsTotal
203
wordsDialogue
31
96.2858%