NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA6G3KX86EM4FGPS7RBGND
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
50.8s
Cost:
$0.009515
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 a decorative shrub, clutching a glittery invitation as if it were a sacred map. Bill adjusted his bowtie, which hid a roll of duct tape and a small grappling hook. They peered through church basement windows where paper crowns and a mound of wrapped mischief blinked under fluorescent lights. This was no ordinary snag; it was a buffet of bows and sticky ribbons. Molly inspected a tiny name tag and imagined tiny footprints and sugar-powered chaos. She smirked, the plan forming like batter: distraction, swoop, vanish. "Ready? Tiptoe, grin, grab every glittery box, no crumbs." Bill licked his thumb, proofed his fake moustache, and whispered back with the seriousness of someone about to purloin birthday joy. He had rehearsed clumsy slips and strategic sneezes. Their rhythm was a tap dance of laws to be bent. The parking lot glowed with inflatable characters, a sentinel clown with a suspicious smile. Molly checked her watch and felt absurdly heroic. Bill nodded and produced a list titled Operation: Presents. "Cake distraction, balloon avalanche, Santa impersonation, laundry exit, fast." Molly tapped his elbow, then delivered a tiny, comically urgent order: "Do it." They melted into shadows, laughing like tiny, victorious thieves.
created_at
"2026-02-16T13:29:12.14416+00:00"
2/16/2026, 1:29:12 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4348
moderation_latency
(null)
generation_time
50515
tokens_prompt
77
tokens_completion
1302
native_tokens_prompt
66
native_tokens_completion
4749
native_tokens_completion_images
0
native_tokens_reasoning
4416
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
0.0095145
router
(null)
provider_responses
0
id
"resp_0c4c5160eaedcfbf0169931b74f3e4819095f6ba975ba6f6c1"
status
200
is_byok
false
latency
126
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248500-7IMuUvTCyN9uvXugLOOz"
upstream_id
"resp_0c4c5160eaedcfbf0169931b74f3e4819095f6ba975ba6f6c1"
total_cost
0.0095145
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: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
99.9995%