NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA1XFG235H2C7BGGTZETC8
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
37.8s
Cost:
$0.007384
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 in the shrubbery outside the community center, clutching a foldable bag like a champion of chaos. Bill juggled a cake-shaped decoy and a flashlight, grin creasing his tired face. They studied the banner announcing Happy Birthday in jaunty letters and a cluster of balloons bobbed, oblivious. Molly traced the layout with a gloved finger, plotting paths between pinatas and snack tables. Every present glowed under fluorescent pity, ribbons promising pocket change turned fortune. They whispered strategies with theatrical seriousness, treating party favors like jewels in a crown. Molly tapped Bill's shoulder and hushed a nearby dog with a sympathetic scratch. Molly: "Bags, masks, cake diversion, swift grabs, quiet exits, no witnesses." Bill's eyes gleamed; he checked his watch like a metronome for mischief. Bill: "We split loot evenly. Children sleep; adults clink. Minimal noise." Night swallowed their laughter as they slid toward the back door, rehearsing clumsy ballet steps. The plan smelled of sugar and adrenaline, of bravery forged in cheap wrapping paper. When the moment came they would move like courteous burglars—gentle, precise, apologetic—leaving empty stockings and perhaps a returned cupcake. They rehearsed whispers, practiced polite footsteps, and agreed on a single ridiculous exit signal together.
created_at
"2026-02-16T13:26:29.387866+00:00"
2/16/2026, 1:26:29 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6755
moderation_latency
(null)
generation_time
37675
tokens_prompt
77
tokens_completion
1003
native_tokens_prompt
66
native_tokens_completion
3684
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
0.0073845
router
(null)
provider_responses
0
id
"resp_0ef62f56cf1cc2270169931adec9948195a1fbb7a65a627b52"
status
200
is_byok
false
latency
129
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248350-ZQgl0wkUVPLJtgI2JX5B"
upstream_id
"resp_0ef62f56cf1cc2270169931adec9948195a1fbb7a65a627b52"
total_cost
0.0073845
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
99.9920%