NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB52Z26S5Z9AHG21R21N5F
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 3s
Cost:
$0.007495
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
They huddled behind a table of party favors, whispering with the theatrical solemnity of bank robbers planning a moonlit confection heist. Molly checked a crumpled blueprint of the living room while Bill practiced a polite smile for diversion. The playlist thumped, children argued over superhero capes, and an exhausted parent refilled juice boxes. Outside, a delivery truck idled like a conspirator. Both checked their watches, adjusted fake name tags, and grinned like thieves who believed they deserved this particular pile of plastic trophies. They loved chaos and cupcakes. Molly: "We slip in after the magician, when everyone's mesmerized and the clown smells faintly of cotton candy." Bill: "And the cake?" Molly: "We swap the cake for a decoy, pockets full, exit through the clown tunnel and we label the boxes for quick lift." Bill: "Gifts or glitter?" Molly: "Gifts, neatly labeled and ribboned, irresistible loot for two professionals. We alphabetize by age, helium balloons as cover." Bill: "What about escape route, and the dachshund?" Molly: "Balloon arch, inflatable slide, straight to the kitchen window." Bill: "Kids awake?" Molly: "If they cry, we look like party helpers, consoling and confetti-armed." Bill: "You sure about confetti?" Molly: "Trust me." Bill: "Fine. Tonight."
created_at
"2026-02-16T13:46:07.053831+00:00"
2/16/2026, 1:46:07 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2806
moderation_latency
(null)
generation_time
62705
tokens_prompt
77
tokens_completion
1155
native_tokens_prompt
66
native_tokens_completion
3739
native_tokens_completion_images
0
native_tokens_reasoning
3392
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
0.0074945
router
(null)
provider_responses
0
id
"resp_04a5cb7312cc0d160169931f5f59d48194a9fa5eacb9cc31cd"
status
200
is_byok
false
latency
127
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249503-C8i3jeoNBEPNqSCkVKGh"
upstream_id
"resp_04a5cb7312cc0d160169931f5f59d48194a9fa5eacb9cc31cd"
total_cost
0.0074945
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
201
100.0000%
Dialogue to Total Word Ratio
Ratio: 50.25%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
101
99.9995%