NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA3JN50T2VAN15SP271HCH
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
31.9s
Cost:
$0.025497
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
In the alley behind the bouncy castle, Molly and Bill whispered. "Bill, remember: it's a children's party, so act wholesome." "Wholesome? I'm in a ski mask shaped like a unicorn." "Perfect. Parents trust unicorns. Now, presents are stacked by the piñata." "Do we take the piñata too? It might contain cash. Or sadness." "No piñata. Too much screaming. We lift the gifts, swap them with decoys." "Decoys?" "Empty boxes filled with broccoli. The real villain is nutrition." "You're a genius, Molly. How do we get inside?" "Through the clown's van. He left it unlocked, because clowns fear nothing." "Then we tiptoe, grab, and vanish." "Vanishing is your department. My department is carrying twelve toy drums." "Grab the quiet gifts first: books, puzzles, anything that doesn't honk." "What about the big one labeled 'For Sophie, from Nana'?" "High value. Grandmas pack receipts and cash like it's warfare." "And if we get caught?" "We smile, say we're entertainers, and hand out broccoli. They'll beg us to leave." "I hate that this might work." "One more thing, Bill: avoid the magician; he can actually tie knots." "Noted. Also, the birthday kid has a drone. If it spots us, I will scream." "Practice smiling."
created_at
"2026-02-16T13:27:18.615852+00:00"
2/16/2026, 1:27:18 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
28482
moderation_latency
(null)
generation_time
31527
tokens_prompt
77
tokens_completion
434
native_tokens_prompt
66
native_tokens_completion
1813
native_tokens_completion_images
0
native_tokens_reasoning
1514
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
0.0254975
router
(null)
provider_responses
0
id
"resp_01db56567722f8120169931b1547b08196aac48193f7ebd50f"
status
200
is_byok
false
latency
157
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771248405-puPPrJHuLaOxDpbQUcVM"
upstream_id
"resp_01db56567722f8120169931b1547b08196aac48193f7ebd50f"
total_cost
0.0254975
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
95.9823%
Dialogue to Total Word Ratio
Ratio: 94.50%, Deviation: 4.50%
neededClean
false
wordsTotal
200
wordsDialogue
189
97.9912%