NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB4BV8Y8GCTEGGY8CNC96Z
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
24.0s
Cost:
$0.019674
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, why are there balloons shaped like dinosaurs on the security perimeter?" "Because, Bill, it’s a children’s party. The dinosaurs are the perimeter." "Right. And the bouncy castle?" "Our distraction. You jump, I swipe." "I’m not bouncing; I’m a professional." "A professional who squeaks when he runs." "That was my shoes, not my soul." Molly adjusted her tiny black beanie, which still had a glittery pom‑pom from the last job. Behind the hedge, the backyard blazed with streamers and sugar. A clown patrolled near the gift table like a heavily armed marshmallow. "Clock it: eight minutes until cake." "Eight minutes? That’s barely enough to loot a bicycle and a chemistry set." "Focus. We take the present pile, dump it in the wagon, vanish through the pinata smoke." "There’s pinata smoke?" "I’m improvising. New intel: the dad is grilling." "Grilling? Like… questions?" "No, sausages. But he looks suspiciously competent." Bill peered over the fence and winced as a toddler locked eyes with him. "She saw me." "Smile." "I’m wearing a mask." "Then wave like you’re hired entertainment." Bill waved. The toddler waved back, then screamed, "MAGIC MAN!" "Perfect," Molly whispered. "They’re already cheering our getaway." Bill sighed, tightening the wagon strap.
created_at
"2026-02-16T13:45:03.935091+00:00"
2/16/2026, 1:45:03 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6616
moderation_latency
(null)
generation_time
23801
tokens_prompt
77
tokens_completion
949
native_tokens_prompt
66
native_tokens_completion
1397
native_tokens_completion_images
0
native_tokens_reasoning
1094
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
0.0196735
router
(null)
provider_responses
0
id
"resp_0d760d50efacb04a0169931f479a248196981ab621b15bc1fb"
status
200
is_byok
false
latency
138
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771249479-vbif9gY8ayV8tgHzDHQQ"
upstream_id
"resp_0d760d50efacb04a0169931f479a248196981ab621b15bc1fb"
total_cost
0.0196735
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
0.1425%
Dialogue to Total Word Ratio
Ratio: 66.00%, Deviation: 16.00%
neededClean
false
wordsTotal
200
wordsDialogue
132
50.0712%