NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAXCFXR7Y78CMRQZ1DHGCD
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 24s
Cost:
$0.043783
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 spread the blueprint over frosting smears, a tactical map of paper crowns and inflatable castles. Bill adjusted his black beanie, which had a sparkly unicorn stitched to the front, a taunt from destiny. The van smelled like sugar and rubber chickens. They were about to infiltrate the most fortified facility known to suburbia: a backyard at peak cupcake hour. "We need tiny shoes, bigger sacks, and excellent balloon camouflage," Molly said, tapping the bouncy house like it owed her money. Bill checked the schedule, which he’d stolen from a magician’s clipboard during rehearsal, complete with glitter fingerprints. "Fine, but clowns bite; bring cake decoys and a map," he replied, practicing a smile that collapsed into a guilty crescent. They rehearsed their route with gummy bears as pawns. The dragon piñata was a sentry; the gift table, a gleaming vault guarded by frosting-glazed grandparents. A sprinkler rotated like a sleepy laser. Somewhere, a dog trained in cupcake retrieval patrolled. Bill pocketed confetti like lock picks. Molly holstered ribbon cutters, holier than knives. Wind chimes whispered code. Over the fence, balloons bobbed, pink periscopes of peril. The playlist escalated; Baby Shark meant chaos cover. At precisely candle blowout, they’d move, unseen.
created_at
"2026-02-16T13:42:15.399431+00:00"
2/16/2026, 1:42:15 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
30252
moderation_latency
(null)
generation_time
83613
tokens_prompt
77
tokens_completion
1435
native_tokens_prompt
66
native_tokens_completion
4370
native_tokens_completion_images
0
native_tokens_reasoning
4032
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
0.0437825
router
(null)
provider_responses
0
id
"resp_0dd8309e57c6d2250169931e62e3908193afb303ae8db92987"
status
200
is_byok
false
latency
201
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771249250-FFY49bbiMnCjxlqh6gzB"
upstream_id
"resp_0dd8309e57c6d2250169931e62e3908193afb303ae8db92987"
total_cost
0.0437825
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%