NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK95SHEWW2Y84NT6QSQGFHT
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
24.2s
Cost:
$0.020051
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 adjusted her cardboard crown. Bill held a gift bag like evidence. "Children's party at two today. We enter as entertainers." "Entertainers? I can't juggle." "Neither can clowns, apparently. We'll fake it." "What's the haul?" "Every present on the table. We swap them with decoys." "Decoys meaning what?" "Empty boxes, wrapped pretty. Kids never notice until Monday." "They notice immediately. They scream like fire alarms." "That's why you bring the bubble machine. Screams become squeals." "I thought the bubble machine was for exit cover." "Both. Bubbles are tactical." "How do we get past the parents?" "You hand out stickers. Adults see stickers and lose all willpower." "And the birthday kid?" "I distract with a magic trick." "You don't know magic." "I know one trick: make presents disappear." "Classic. Any getaway?" "Piñata. We hide the gifts inside." "Inside a piñata?" "Yes, then we carry it out 'for later.'" "They'll want to smash it now." "Not if you announce it's filled with broccoli." "You're a monster." "Focus, Bill. Costumes?" "I've got a mascot head." "Perfect. Which animal?" "Depressed shark." "Great. Kids love emotional complexity." "What about me?" "Princess. Every heist needs royalty." "Fine, but if glitter gets on my crowbar, I'm suing."
created_at
"2026-02-16T13:10:53.723567+00:00"
2/16/2026, 1:10:53 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
20466
moderation_latency
(null)
generation_time
23742
tokens_prompt
77
tokens_completion
460
native_tokens_prompt
66
native_tokens_completion
1424
native_tokens_completion_images
0
native_tokens_reasoning
1116
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
0.0200515
router
(null)
provider_responses
0
id
"resp_0e61377aef0a639e01699317458bec81958a2db17f5f033d34"
status
200
is_byok
false
latency
145
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247429-o7NTYRUZpmhatoU9gPS4"
upstream_id
"resp_0e61377aef0a639e01699317458bec81958a2db17f5f033d34"
total_cost
0.0200515
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
97.4725%
Dialogue to Total Word Ratio
Ratio: 94.00%, Deviation: 4.00%
neededClean
false
wordsTotal
200
wordsDialogue
188
98.7362%