NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKATW3A0DAM1JGG1XG1AFCZ
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
34.1s
Cost:
$0.008209
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 whispered beside the birthday cake. Molly: Tonight we steal paper ribbons and bubble wrap and maybe cake. Bill: Cake? We are thieves, not dessert dredgers. Molly: Children nap, parents watch grownup magic shows, we move like confetti. Bill: Confetti has no thumbs. Focus. I scout the nap zone, you snag gifts. Molly: Wraps rustle, squeaky toys betray, but I have a strategy involving balloons and a kazoo. Bill: A kazoo? That is either brilliant or a federal offense. Molly: Both. We label each gift "temporary guardian" and slip them into my bag. Bill: How big is your bag? Molly: Big enough for five dragons and a questionable doll collection. Bill: Dragons are heavy. Are we stealing dragons too? Molly: Only the inflatable kind. We will trade cake crumbs as distraction. Bill: I will wear a party hat and a somber mustache. Molly: We will exit through the ball pit, obviously. Bill: Obvious is my middle name. Molly: Mine is "Probably Not." Bill: Then let's be professional. Molly: Professional amateurs with impeccable timing. Bill: At three, we go. Molly: At three, we go. Bill: Smile and juggle cupcakes while I hold the flashlight. Molly: Also distract them with balloon art.
created_at
"2026-02-16T13:40:03.983171+00:00"
2/16/2026, 1:40:03 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7008
moderation_latency
(null)
generation_time
33907
tokens_prompt
77
tokens_completion
987
native_tokens_prompt
66
native_tokens_completion
4096
native_tokens_completion_images
0
native_tokens_reasoning
3776
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
0.0082085
router
(null)
provider_responses
0
id
"resp_02f27c40be2c81100169931e10908c81908ba16b0a9a9c9192"
status
200
is_byok
false
latency
128
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249168-YRjkC0dbthJQzrV9pkh0"
upstream_id
"resp_02f27c40be2c81100169931e10908c81908ba16b0a9a9c9192"
total_cost
0.0082085
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
0.0000%
Dialogue to Total Word Ratio
Ratio: 2.00%, Deviation: 88.00%
neededClean
false
wordsTotal
200
wordsDialogue
4
50.0000%