NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9ER11A97W9VM3P847K7NX
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 5s
Cost:
$0.012061
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 perched on the windowsill like a patient cat, peering at a living room littered with balloons and a vivid mountain of gift wrap. She and Bill rehearsed their practiced whispers, scheming like burglars from a children’s storybook. Bill balanced a collapsible ladder and an expression that said he regretted every life choice that led to midnight present acquisition. They checked lists: sugar levels, clown attendance, escape routes, and whether the piñata counted as heavy loot. The plan was simple, absurd, and inevitably sticky. They would swap the dog with a stuffed animal, distract adults with charming nonsense, then vanish with armfuls of glittering rectangles. Molly smirked, polish on her voice, "Presents only. No cake. No one cries over missing socks." while Bill adjusted his mittened gloves like a nervous bank robber. "Silent like ninjas, fast like cheetahs, generous only to ourselves." Outside, a sprinkling of confetti snowed from the gutters. Somewhere inside, a chorus of giggles marked where treasure slept beneath streamers. The clock winked toward party cake o'clock and their window of opportunity tightened into a sliver of daring. They practiced the graceful grab, timing breaths as if rehearsing a ridiculous ballet. And their shoes betrayed them often.
created_at
"2026-02-16T13:16:28.23642+00:00"
2/16/2026, 1:16:28 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11432
moderation_latency
(null)
generation_time
64751
tokens_prompt
77
tokens_completion
1401
native_tokens_prompt
66
native_tokens_completion
6022
native_tokens_completion_images
0
native_tokens_reasoning
5696
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
0.0120605
router
(null)
provider_responses
0
id
"resp_05eefdaf07604896016993186aa21c81978a7a9547499279b3"
status
200
is_byok
false
latency
125
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771247722-KIiJp288yfgrIqLrVRsG"
upstream_id
"resp_05eefdaf07604896016993186aa21c81978a7a9547499279b3"
total_cost
0.0120605
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
100.0000%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%