NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9XD6R78V57TF91NK7ZRAE
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
42.3s
Cost:
$0.008616
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 and Bill crouched behind a sagging hedge, whispering as if nursery rhymes might tattle. They had rehearsed routes between cartoon shadows, practiced graceful larceny around tiny plastic dinosaurs, and debated glitter. Tonight's target smelled like frosting and parental optimism. Their toolkit was absurd: a child's umbrella, a flashlight that only flashed disco, and a grocery bag labeled DONATIONS. Molly smirked, tapping a paper map with a crayon dot for the cake table. "Tiptoe, snag gifts, avoid cake, pocket confetti, exit through pantry." "One teddy stays, swap list, duct-tape balloons, vanish under piƱata." They reviewed timings; balloons popped into villains in their heads. Bill checked a watch that had never kept time, which suited them fine because chaos never consulted schedules. They planned a silent entrance through the pantry, a whisper corridor past sleeping clowns, a graceful scoop of wrapped carnivals. If a child stirred they'd leave one perfect stuffed animal on the pillow, a ransom of cuddles, and vanish leaving only giggles behind. Their heist would be surgical, ridiculous, and small-hearted: liberating presents from the tyranny of good behavior charts and sticky hands. As lights dimmed, they readied tools and practiced a whisper laugh, and checked the lock twice.
created_at
"2026-02-16T13:24:06.099754+00:00"
2/16/2026, 1:24:06 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4606
moderation_latency
(null)
generation_time
42174
tokens_prompt
77
tokens_completion
1468
native_tokens_prompt
66
native_tokens_completion
4300
native_tokens_completion_images
0
native_tokens_reasoning
3968
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
0.0086165
router
(null)
provider_responses
0
id
"resp_08d7172c7b5d57240169931a4b0ea08197af8683564b2784f2"
status
200
is_byok
false
latency
143
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248202-TnHt2eOpiSP1HwILiJDn"
upstream_id
"resp_08d7172c7b5d57240169931a4b0ea08197af8683564b2784f2"
total_cost
0.0086165
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
99.9998%
Dialogue to Total Word Ratio
Ratio: 10.40%, Deviation: 0.40%
neededClean
false
wordsTotal
202
wordsDialogue
21
99.9919%