NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-16-01KHK9731QK0MNRTP8F92N6PX4
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 6s
Cost:
$0.058048
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
Overall
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
“Bill: Molly, it’s a kid’s party. Balloons, clowns, and the kind of screaming that summons cops.” “Molly: Perfect. Screaming is cover. Presents are cash wearing paper.” “Bill: Tell me again why we’re not robbing a bank.” “Molly: Because banks have locks. This place has juice boxes and trust.” “Bill: Fine. How do we get in?” “Molly: We stroll in. You carry a cake. I carry a clipboard. People worship clipboards.” “Bill: What’s on it?” “Molly: Nothing. Empty authority still pays dividends.” “Bill: Then what?” “Molly: We ‘organize’ the gift table. All those bags into one convenient pile.” “Bill: They’re wrapped in dinosaurs.” “Molly: So are rich people’s mistakes. We don’t open them.” “Bill: Complications?” “Molly: Birthday dad’s an off-duty cop.” “Bill: You knew?” “Molly: I invited him. He’ll be busy pretending to be fun.” “Bill: If he spots us?” “Molly: We put a party hat on him. No one arrests a criminal while wearing a rainbow cone.” “Bill: And the kids?” “Molly: Piñata early. Candy blizzard. Adults panic. We exit with the ‘safety donations.’” “Bill: I can’t say ‘safety donations’ without sweating confetti.” “Molly: Smile. Nothing scares parents like a serious adult.” “Bill: What if the pony recognizes me again?”
created_at
"2026-02-16T13:12:17.727123+00:00"
2/16/2026, 1:12:17 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
62617
moderation_latency
(null)
generation_time
65659
tokens_prompt
77
tokens_completion
372
native_tokens_prompt
66
native_tokens_completion
4138
native_tokens_completion_images
0
native_tokens_reasoning
3813
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
0.0580475
router
(null)
provider_responses
0
id
"resp_03064ba424a7830e016993176fc79881949f1c7d7d1f35cb99"
status
200
is_byok
false
latency
196
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247471-wvZslw9RTcwmoWzfydtZ"
upstream_id
"resp_03064ba424a7830e016993176fc79881949f1c7d7d1f35cb99"
total_cost
0.0580475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3940%