NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKARZYHBRVW18DEV45DN2Q6
Run Details
Model:
GPT-5.2
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
32.1s
Cost:
$0.029264
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
"So the vault is a bouncy castle," Molly whispered. "With a clown on patrol," Bill said. "Clowns can't see in the dark," Molly said. "But the candles are shaped like dinosaurs," Bill muttered. Outside the community center, they crouched behind a minivan painted with smiling giraffes. A chorus of children sang off-key, a soundtrack for larceny. "We go during the piƱata," Molly said. "Everyone will be blinded by sugar and violence," Bill said. Molly checked her duffel, already lined with tissue paper stolen from last Christmas. "Grab the gift bags, not the cake," Molly warned. "I learned that lesson at the baptism," Bill sighed. "Masks?" Molly asked. Bill flicked open a box of glittery cones. "Party hats. Nobody questions a cone," Bill replied. "And the getaway?" Molly said. "Toy wagon. It squeaks, but it blends," Bill said. Someone inside screamed with joy; Bill flinched anyway. Molly adjusted her fake mustache and listened carefully. "Fine. If a child offers you juice, take it," Molly said. "And if a parent asks our names?" Bill asked. "You're 'Fun Uncle.' I'm 'Responsible Aunt.' Try not to improvise," Molly said. Bill saluted with a sticker sheet. "I never improvise. Mostly. Today." Bill grinned.
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
29513
moderation_latency
(null)
generation_time
31589
tokens_prompt
77
tokens_completion
305
native_tokens_prompt
66
native_tokens_completion
2082
native_tokens_completion_images
0
native_tokens_reasoning
1785
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
0.0292635
router
(null)
provider_responses
0
id
"resp_0c913c3fd1051e9f0169931dd3055481979c5735954ec6e862"
status
200
is_byok
false
latency
173
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771249106-ndOaOQR3voaFVtAeY7FT"
upstream_id
"resp_0c913c3fd1051e9f0169931dd3055481979c5735954ec6e862"
total_cost
0.0292635
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
199
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
199
wordsDialogue
100
99.9995%