NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK98EDVKW6TA6C1TV3YS3DP
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
25.4s
Cost:
$0.021004
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 unfolded a glittery city map on the hood of their dented van. Bill’s clown wig sat beside a crowbar, shedding red curls like incriminating evidence. From the nearby park drifted squeals, pop music, and the sweet smell of buttercream—security systems for the morally vulnerable. Molly tapped the route: through the side gate, past the bouncy castle, straight to the gift table piled like a tiny dragon’s hoard. Bill practiced a silent tiptoe and nearly slipped on a sprinkle he’d tracked in. They listened for sirens; only a kazoo answered. He sighed, zipped shoes, and muttered a prayer to frosting. "Tonight's target is a six-year-old's party, Bill." "Finally, a crowd that screams before they call the cops." "We enter as clowns, grab gifts, and vanish in confetti." "I refuse balloon animals; my last giraffe looked like a worm." "No balloons. You'll carry the loot sack labeled 'Donations'." "Won't parents notice us stealing their kid's happiness?" "Parents are busy filming; they'll assume it's a magic trick." "What about the birthday boy? He bites." "Bribe him with cake, then swap the presents for decoys." "Decoys like what, exactly, besides my dignity?" "Empty boxes, rocks, and a polite note: 'Thanks for sharing, kid.'"
created_at
"2026-02-16T13:12:21.799294+00:00"
2/16/2026, 1:12:21 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
22255
moderation_latency
(null)
generation_time
25177
tokens_prompt
77
tokens_completion
442
native_tokens_prompt
66
native_tokens_completion
1492
native_tokens_completion_images
0
native_tokens_reasoning
1201
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
0.0210035
router
(null)
provider_responses
0
id
"resp_0c7a9cf6a3aad72f016993179c2bb88197bee74cb6b3a69df3"
status
200
is_byok
false
latency
166
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247516-UgJMyjjfGA7Jv40vVJFS"
upstream_id
"resp_0c7a9cf6a3aad72f016993179c2bb88197bee74cb6b3a69df3"
total_cost
0.0210035
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
203
wordsDialogue
102
99.9595%