NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9749JXD1J98P61PVNRSCD
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 36s
Cost:
$0.079215
Provider:
OpenAI
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 and Bill crouched behind a hedge, watching a backyard children’s party throb with balloons and syrupy pop music. A clown inflated a sausage dog; the kids applauded as if witnessing the birth of comedy. Beyond the sprinkler, a folding table sagged under neatly wrapped presents, each bow screaming, Take me. Bill’s beanie still carried glitter from last week’s job, so he tucked it into his pocket like contraband. Molly traced the side gate with her eyes, timing the patrols of parents wielding paper plates and suspicious kindness. Somewhere, a piñata waited, blind and judgmental. The birthday song began rehearsing. "Rule one, Bill: act festive." "Hard when my soul wears burglary pants." "Smile anyway. We enter during the birthday song, grab gifts, exit before candles die." "Which gifts?" "Big boxes first, then the dinosaur ones." "Dinosaur ones for you?" "For the kid; I’m not a monster." "What about unicorn paper?" "Glitter is fingerprints that never stop talking." "If the clown sees us?" "Then we tell him we’re party magicians and vanish with the loot." "Should we leave a card?" "Yes: Love, Aunt Molly and Uncle Bill." "Sounds honest." "It’s a crime; honesty is optional. Ready?" "My knees shake confetti. Go."
created_at
"2026-02-16T13:12:49.161937+00:00"
2/16/2026, 1:12:49 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21077
moderation_latency
(null)
generation_time
95060
tokens_prompt
77
tokens_completion
1151
native_tokens_prompt
66
native_tokens_completion
5650
native_tokens_completion_images
0
native_tokens_reasoning
5366
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
0.0792155
router
(null)
provider_responses
0
id
"resp_07225580477997b20169931771044c81958c713d1ba372b750"
status
200
is_byok
false
latency
160
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247472-AYMFQLadNpCBPcutvvgC"
upstream_id
"resp_07225580477997b20169931771044c81958c713d1ba372b750"
total_cost
0.0792155
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%