NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAS927ZQTSEVXXQ7N0ABWC
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
22.8s
Cost:
$0.019869
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: Midnight, backyard trampoline, balloons everywhere. We slip in during 'Happy Birthday.' Bill: Children's parties have security? Molly: Parents. Worse. They ask questions. Bill: Like, 'Why are you in the gift pile, sir?' Molly: Exactly. So we wear party hats. Criminal camouflage. Bill: I refuse the dinosaur hat. It makes me look like an accountant. Molly: Then wear the unicorn one. Nobody suspects a unicorn. Bill: Unicorns are suspiciously magical. Molly: Focus. Presents are stacked by the bouncy castle. We grab, exit through the side gate. Bill: What about the clown? Molly: Clown's on our payroll. Bill: We have payroll? Molly: I tipped him in balloon animals. He owes us. Bill: Great. What's the signal? Molly: When I yell, 'Who wants more juice?' you scoop the loot. Bill: And if someone says, 'Me'? Molly: Give them a juice box, take their Nintendo. Bill: Morally confusing. Molly: It's a heist, Bill. Bill: Any contingencies? Molly: If confronted, we claim we're the entertainment. Bill: I can't juggle. Molly: You can juggle lies. Bill: True. What about dogs? Molly: Bribe with hot dogs. Bill: And if the birthday kid recognizes us? Molly: We sign autographs: 'To Timmy, love, Santa.' Now grab the glitter."
created_at
"2026-02-16T13:38:59.915245+00:00"
2/16/2026, 1:38:59 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5329
moderation_latency
(null)
generation_time
22571
tokens_prompt
77
tokens_completion
959
native_tokens_prompt
66
native_tokens_completion
1411
native_tokens_completion_images
0
native_tokens_reasoning
1090
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
0.0198695
router
(null)
provider_responses
0
id
"resp_09b3f6617702f6020169931ddc5180819080d2d753e8001c4d"
status
200
is_byok
false
latency
191
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771249116-6jQNzmDukwnGzhMB7x5W"
upstream_id
"resp_09b3f6617702f6020169931ddc5180819080d2d753e8001c4d"
total_cost
0.0198695
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
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
200
68.3940%