NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAV73217ZDC5VDW9MNKHNH
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
47.5s
Cost:
$0.039399
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 inflatable castle, smelling frosting and impending felony. Bill adjusted his black beanie, which had “HAPPY BIRTHDAY” stitched on it in glitter. The backyard pulsed with squeals, kazoo music, and a piñata that looked armed. A clown watched them, suspiciously polishing a balloon sword nearby. “We go in when they sing,” Molly whispered. “Everyone closes eyes, mouths open, brains off, like always, Bill.” Bill frowned. “But the song is long. Can we steal by the chorus?” “No,” she said. “We need clean hands. Grab bags only. We’re professionals, not raccoons.” Bill peeked at the gift table, stacked like a glittering pyramid. “How many presents is ‘all’?” “All,” Molly said. “Every box, every bow. Even the weird ones shaped like dinosaurs.” “And the birthday kid?” “We leave him,” she said. “He’s loud and legally protected.” Bill tugged on a paper party hat. “My disguise is insulting.” “Your face is insulting,” Molly said. “Hat helps.” The host clapped. Candles flared. Molly slid on knee pads. Bill whispered, “If we get caught, we say we’re entertainers.” Molly nodded. “Sure. You juggle guilt, I’ll mime innocence.” “Deal,” Bill said. “On three?” “On ‘make a wish,’” Molly replied, grinning, “we make ours.”
created_at
"2026-02-16T13:40:27.505958+00:00"
2/16/2026, 1:40:27 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5045
moderation_latency
(null)
generation_time
46846
tokens_prompt
77
tokens_completion
1098
native_tokens_prompt
66
native_tokens_completion
2806
native_tokens_completion_images
0
native_tokens_reasoning
2493
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
0.0393995
router
(null)
provider_responses
0
id
"resp_0ea46c6036f9fb790169931e1bd52881909c5c441c9d0ba347"
status
200
is_byok
false
latency
158
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771249179-xf4xBjgwXaJyg0pe5wq9"
upstream_id
"resp_0ea46c6036f9fb790169931e1bd52881909c5c441c9d0ba347"
total_cost
0.0393995
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
99.6101%
Dialogue to Total Word Ratio
Ratio: 52.50%, Deviation: 2.50%
neededClean
false
wordsTotal
200
wordsDialogue
105
99.8051%