NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA3KT810XR8CK043HPTV5N
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
41.6s
Cost:
$0.009130
Provider:
OpenAI
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
Molly and Bill crawled into the pastel-lit living room like a pair of misfit raccoons, clutching a lumpy duffel and a plan stitched from sugar and bravado. Balloons bobbed above a mountain of bows and glittering boxes. A plastic princess tiara snagged on the rug, reminding Molly why she loved childhood crime: easy targets, ridiculous rewards. Bill checked his watch and winked at a deflated balloon. They whispered over a spread of paper hats and a half-eaten cupcake, sketching escape routes between streamers. They practiced silent footsteps over crinkled wrapping paper, rehearsing the polite pluck of ribbons. Their map was simple: distract with the punch bowl, extract the Santa sacks, vanish beneath a tulle avalanche. Molly traced the route with a finger, savoring the smell of frosting and opportunity. Bill balanced a teddy bear on his shoulder like a lookout, solemn as an opera conductor. Outside, the party's laughter swelled; inside, their hearts drummed a comical march. Tension mingled with absurdity — a heist so sweet it needed a napkin. They grinned at the absurdity together. "First the cake, then the loot, leave no stuffed animal behind," Molly breathed. "And don't eat the evidence, especially not the glitter," Bill hissed.
created_at
"2026-02-16T13:27:28.546358+00:00"
2/16/2026, 1:27:28 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2325
moderation_latency
(null)
generation_time
41411
tokens_prompt
77
tokens_completion
1248
native_tokens_prompt
66
native_tokens_completion
4557
native_tokens_completion_images
0
native_tokens_reasoning
4224
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0091305
router
(null)
provider_responses
0
id
"resp_0404713f27ce50150169931b167e048190be15c08404dd30de"
status
200
is_byok
false
latency
158
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248406-7lqPz7hpGCg1Xxtk0pmh"
upstream_id
"resp_0404713f27ce50150169931b167e048190be15c08404dd30de"
total_cost
0.0091305
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
99.9995%