NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9CDHSSD0SQ68DM480B6XD
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
56.8s
Cost:
$0.044006
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 the hedge across from the backyard. Paper lanterns bobbed quietly. Through the fence slats, children shrieked over a piƱata shaped like a unicorn with tax problems. Bill adjusted his clip-on bow tie; it still had a price tag. Molly unzipped a duffel bag and revealed party hats, a rubber chicken, and three lengths of rope that looked suspiciously like 'balloon animals.' A stroller rolled past on the sidewalk, and they froze, pretending to study a map. The stroller was empty. From the gate, a clown honked, inviting them in. "You're sure it's a children's party?" Molly whispered. "Absolutely. Balloons, clown, sugar crash scheduled for eight." Bill said. "Good. Their security consists of a dad with a phone." Molly said. "We go in as entertainers. I juggle guilt and hotdogs." "I'll be the magician. Watch: your wallet vanishes." "Focus, Molly. We're here for presents, not petty cash." "Presents are petty cash with wrapping paper and screams." "How do we carry them out without looking like monsters?" "Easy. We 'donate' them to our van for 'extra games'." "And if a kid asks where his robot went?" "Tell him it's on a secret mission. He'll respect that." "Deal."
created_at
"2026-02-16T13:15:03.529654+00:00"
2/16/2026, 1:15:03 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
33821
moderation_latency
(null)
generation_time
56466
tokens_prompt
77
tokens_completion
1254
native_tokens_prompt
66
native_tokens_completion
3135
native_tokens_completion_images
0
native_tokens_reasoning
2848
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
0.0440055
router
(null)
provider_responses
0
id
"resp_09805eda1e240989016993181e5b588195b18bce32add0f622"
status
200
is_byok
false
latency
169
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247646-bLTlxo8uUiZNtgkNZJNT"
upstream_id
"resp_09805eda1e240989016993181e5b588195b18bce32add0f622"
total_cost
0.0440055
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
63.5019%
Dialogue to Total Word Ratio
Ratio: 58.21%, Deviation: 8.21%
neededClean
false
wordsTotal
201
wordsDialogue
117
81.7505%