NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9X4A4TC3QR3TVFF8THK8F
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
38.3s
Cost:
$0.030720
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 crouched behind the hedge, party hat bobbing on her head like a guilty flag. Through the window, toddlers shrieked around a volcano cake while a clown handed out balloons shaped like swords. "Bill, why are we wearing party hats?" Molly whispered. "Camouflage," Bill said. "If anyone asks, we're the entertainment. You do a rabbit. I do taxes." "We're stealing presents, not traumatizing children." "Focus. Big box by the table—remote-control drone. Small bags—candy. We sweep, we leave." Molly peeked at the gift pile. A banner read HAPPY SIXTH, EMMA! in glitter. "I feel weird," she said. "What if the kid wants the drone?" "Then she'll learn about loss early," Bill replied. "Character-building. Now, entry point?" "Back door. It sticks. I saw Dad shoulder it open." Bill adjusted his black gloves, which squeaked like rubber ducks. "We go in during 'Pin the Tail.' Everyone's blindfolded." "And if they catch us?" "We say we're 'party auditors' and confiscate unlicensed joy." Molly sighed. "Fine. But I'm taking the goody bags too." "Take two. We're professionals." Outside, a piñata swung in the yard like a safe. Molly and Bill slipped to the back door stepping over bubbles timing their breaths to the birthday song.
created_at
"2026-02-16T13:23:52.880961+00:00"
2/16/2026, 1:23:52 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6062
moderation_latency
(null)
generation_time
37961
tokens_prompt
77
tokens_completion
1050
native_tokens_prompt
66
native_tokens_completion
2186
native_tokens_completion_images
0
native_tokens_reasoning
1888
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
0.0307195
router
(null)
provider_responses
0
id
"resp_0e7224829e24e9490169931a41f1d48195bda1491163299a31"
status
200
is_byok
false
latency
143
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771248193-Q9UeIeIeolHJmc1OXqUP"
upstream_id
"resp_0e7224829e24e9490169931a41f1d48195bda1491163299a31"
total_cost
0.0307195
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
98.6232%
Dialogue to Total Word Ratio
Ratio: 53.43%, Deviation: 3.43%
neededClean
false
wordsTotal
204
wordsDialogue
109
99.1838%