NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAKAKD3WM3J6GGKZ8NJ5DQ
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
38.2s
Cost:
$0.038476
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crouched behind the bouncy castle like it was a bank vault, its vinyl walls breathing strawberry-scented air. Bill held binoculars upside down, whispering updates to no one in particular, while a clown marched past carrying a tray of juice boxes like cash. The backyard glittered with streamers and the kind of vigilant parents who could spot a lie from across a sandbox. They had cased museums and mansions, but nothing prepared them for the strategic chaos of eight-year-olds. A piñata hung in the center like a dangling alarm system. Each shriek from the slip ’n slide made Bill flinch, as if the lawn itself might call the cops. Molly checked her pockets: gloves, zip ties, a tiny crowbar, and a party hat for “blend-in” purposes. Bill had brought a duffel bag labeled DONATIONS, which felt optimistic. “After cake, we slip in. Quiet hands.” Molly winked. Bill swallowed. “If they ask our names, Bill?” “Smile; parents forget adults, kids forget all,” she said. Across the fence, the birthday child opened a gift, and the crowd roared. Molly’s eyes narrowed, reverent. Tonight, they weren’t stealing treasure. They were stealing joy in bulk, gift-wrapped and taped crookedly, waiting to be liberated carefully.
created_at
"2026-02-16T13:36:00.102805+00:00"
2/16/2026, 1:36:00 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6037
moderation_latency
(null)
generation_time
37888
tokens_prompt
77
tokens_completion
1075
native_tokens_prompt
66
native_tokens_completion
2740
native_tokens_completion_images
0
native_tokens_reasoning
2457
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
0.0384755
router
(null)
provider_responses
0
id
"resp_04efc3c2f957ca320169931d1967f0819799fee900688b0f7f"
status
200
is_byok
false
latency
183
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771248921-rRnb8k2BxWwfPVKQ6ais"
upstream_id
"resp_04efc3c2f957ca320169931d1967f0819799fee900688b0f7f"
total_cost
0.0384755
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.7443%
Matches word count
n/a
neededClean
false
words
204
99.9999%
Dialogue to Total Word Ratio
Ratio: 10.29%, Deviation: 0.29%
neededClean
false
wordsTotal
204
wordsDialogue
21
99.8721%