NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9G5D76NQN00F4VKE2MM1F
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
27.7s
Cost:
$0.023622
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 rented bouncy castle, studying the backyard like a general with frosting on her boot. Through the fence slats, toddlers swarmed a table piled with gift bags, each one crinkling with the promise of batteries and noisy plastic. Bill adjusted his black beanie, which was currently decorated with a stray sprinkle, and tried to look less like a man about to commit grand larceny against kindergarteners. A clown juggled oranges and a suspiciously sharp set of steak knives, while a dad in flip-flops guarded the cooler as if it held state secrets. “In, out, nab presents, leave.” Molly’s whisper tasted of bubblegum stolen from an earlier, more dignified crime. “At a kids’ party?” Bill asked, watching a child body-slam a piñata with professional fury. “They won’t notice.” “I will.” “Smile, wave, blame the magician.” “Deal.” They waited for the birthday song, counting claps like a safecracker counts tumblers. When the candles flared, Molly slipped on a tiny cape, Bill grabbed a stack of gift bags, and together they drifted toward the loot, applauding loudly, like loyal relatives with very large pockets. The toddlers cheered, the parents filmed, and nobody questioned why Uncle Bill was sweating confetti today.
created_at
"2026-02-16T13:16:37.210563+00:00"
2/16/2026, 1:16:37 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14650
moderation_latency
(null)
generation_time
27405
tokens_prompt
77
tokens_completion
905
native_tokens_prompt
66
native_tokens_completion
1679
native_tokens_completion_images
0
native_tokens_reasoning
1397
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
0.0236215
router
(null)
provider_responses
0
id
"resp_084308b876303970016993189929e0819086c9ed56d7b78386"
status
200
is_byok
false
latency
163
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771247769-hPZz4pKVDRZMXzsGRx2m"
upstream_id
"resp_084308b876303970016993189929e0819086c9ed56d7b78386"
total_cost
0.0236215
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
99.9920%