NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK98D3VMJJND666JTBW051Y
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
56.2s
Cost:
$0.049256
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 crouched behind an inflatable unicorn, watching the yard pulse with ukulele music and frosting fumes. A banner yelled HAPPY SEVENISH. Bill adjusted his black beanie and tried to look like a dad who understood juice boxes. The prize sat beside the bouncy castle: a glittering hill of presents, bows like emergency parachutes. Their heist was simple: drift in during the piñata riot, load a trash bag, exit through the side gate. Complication: a clown guarded the perimeter, stalking in slow circles with a bubble machine that hissed like a tiny dragon. "Stay low. Grab unlabeled stuff," Molly murmured. Bill peered at the tags. "Everything’s labeled. We take gift cards." The piñata swung and missed again; candy finally burst out, and children swarmed the lawn like piranhas in party hats. Molly and Bill slid forward, smiling with painful friendliness, hands already scooping. "Clown’s watching. Smile like parents," Molly warned. "I forgot how today," Bill said, his grin creaking. A ribbon squeaked under his fingers. The clown’s head snapped toward them, red nose twitching. Molly calmly lifted a stack of envelopes from the card table and waved, as if she belonged to somebody’s PTA. Behind her, Bill bagged stickers, then reconsidered.
created_at
"2026-02-16T13:12:51.661946+00:00"
2/16/2026, 1:12:51 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5585
moderation_latency
(null)
generation_time
55862
tokens_prompt
77
tokens_completion
1082
native_tokens_prompt
66
native_tokens_completion
3510
native_tokens_completion_images
0
native_tokens_reasoning
3228
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
0.0492555
router
(null)
provider_responses
0
id
"resp_0976eb6101fc672d016993179ad82c8194b05a34d961148ba1"
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-1771247514-v9dTZ9YAGIOADKQnFkQG"
upstream_id
"resp_0976eb6101fc672d016993179ad82c8194b05a34d961148ba1"
total_cost
0.0492555
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%