NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAMJY4R78RZS4A2A8FZ8CT
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
43.8s
Cost:
$0.007516
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
Porch smelled of cake glitter. Molly: Do you smell frosting or is that my conscience? Bill: Frosting, definitely frosting. Conscience is on vacation with a napkin. Molly: We go in, scoop presents, exit before anyone notices the missing chaos. Bill: Scoop? Like an ice cream scoop? Because I brought a spoon and it's terrible for locks. Molly: No locks, Bill. We distract with balloon animals and a kazoo solo. Bill: A kazoo? You trust my kazooing abilities for a felony? Molly: I trust your kazoo to clear a room. Also, your juggling leaves people speechless. Bill: My juggling is a public service. Kids will clap and forget their own birthdays. Molly: Perfect. You play the sad clown, I play the generous fairy pretending to misplace magic dust. Bill: And the parents will follow us to return the 'dust', leaving piles of gifts unattended? Molly: They'll follow like kids to a bubble machine. Then we politely wrap everything and slide it into our bag. Bill: Politely wrap? Since when did you learn etiquette? Molly: Since reading three etiquette blogs during lunch. Also, scissors are for ribbon, not eyebrows. Bill: Final question: cake? Molly: Cake is collateral. We each take one slice.
created_at
"2026-02-16T13:36:46.939337+00:00"
2/16/2026, 1:36:46 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
34767
moderation_latency
(null)
generation_time
43550
tokens_prompt
77
tokens_completion
679
native_tokens_prompt
66
native_tokens_completion
3750
native_tokens_completion_images
0
native_tokens_reasoning
3456
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
0.0075165
router
(null)
provider_responses
0
id
"resp_09246ec5eb7e45760169931d42958881979ec37f0717761bc7"
status
200
is_byok
false
latency
131
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248962-c6l1qYAqd1mIODGvklF6"
upstream_id
"resp_09246ec5eb7e45760169931d42958881979ec37f0717761bc7"
total_cost
0.0075165
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: 3.00%, Deviation: 87.00%
neededClean
false
wordsTotal
200
wordsDialogue
6
50.0000%