NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK97WKM72BK6S2B66PX9D5Q
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
22.4s
Cost:
$0.019127
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
The community hall smelled of frosting and plastic balloons, a battlefield of glitter. Molly crouched behind the stacked folding chairs, watching parents herd sugar-drunk toddlers into a conga line around the piƱata. Bill adjusted his black beanie, which made him look less like a criminal and more like an anxious librarian. "Five minutes," Molly whispered. "Grab ribbons too," Bill said. Their plan was elegant: arrive during the magic show, vanish with the gift mountain, exit through the kitchen like two well-dressed caterers. Molly had even brought a clipboard, because nobody questions clipboards. Bill carried a duffel bag that read HAPPY BIRTHDAY, a repurposed souvenir from his last job. A clown shouted something about invisible elephants. The kids screamed in agreement. "No screaming," Molly warned. "We're professionals," Bill muttered. "And cake?" Bill asked. Molly pointed at the presents: dinosaur boxes, glitter bags, suspiciously heavy rectangles that could only be board games or tiny dumbbells. She timed the lull, then slid forward, smiling at a dad who assumed she was on the party committee. Bill followed, bowing slightly, as if the gifts were royalty. The first box squeaked. Everyone clapped, thankfully at the clown. Molly winked, and their duffel began swallowing joy.
created_at
"2026-02-16T13:12:01.201305+00:00"
2/16/2026, 1:12:01 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21035
moderation_latency
(null)
generation_time
22050
tokens_prompt
77
tokens_completion
336
native_tokens_prompt
66
native_tokens_completion
1358
native_tokens_completion_images
0
native_tokens_reasoning
1081
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
0.0191275
router
(null)
provider_responses
0
id
"resp_0cbaf260f52e153d0169931789faa0819580cefbb5f11dc72d"
status
200
is_byok
false
latency
197
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247497-iLsVDOdRdCMoHsrbhXHs"
upstream_id
"resp_0cbaf260f52e153d0169931789faa0819580cefbb5f11dc72d"
total_cost
0.0191275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
95.7885%
Dialogue to Total Word Ratio
Ratio: 5.45%, Deviation: 4.55%
neededClean
false
wordsTotal
202
wordsDialogue
11
97.8863%