NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKARDK1V5VQ7072SC0MAAD0
Run Details
Model:
GPT-5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1m 16s
Cost:
$0.045902
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Behind the hedges, they reviewed a crayon map taped to a pizza box, translating strategy into confidence. Molly rehearsed smiles in a compact mirror, practicing an expression that said volunteer while her pockets whispered larceny. Bill stretched hamstrings like a gymnast, flexing for the bouncy gauntlet. The backyard throbbed with machines and sugar storms; a banner declared Max Is Five in heroic glitter. A labradoodle patrolled wearing a cape, tail archived evidence on passing shins. Their duffel held tissue paper silencers, candle snuffers, and a superhero sticker bribe. A whistle blew. Timetable advanced. They bumped fists, then tiptoed toward destiny. "Bill, our target is a unicorn cake perimeter with balloons." "Molly, you plan like a magician who coupons for chaos." "Disguises: face paint, party hats, smiles set to mischief tonight." "And we mingle, compliment juice boxes, then liberate gift mountains." "Remember, step lightly; toddlers sense guilt like sharks smell sprinkles." "I trained by babysitting triplets; negotiation with raisins hardened me." "Route: bounce house, under slide, left at defeated piƱata confetti." "What about the clown, the one radiating unlicensed emotional honesty?" "Decoy him with a kazoo; clowns respect improvisational wind instruments." "Perfect. After grab, we gift ourselves alibis wrapped in innocence."
created_at
"2026-02-16T13:39:24.333277+00:00"
2/16/2026, 1:39:24 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9604
moderation_latency
(null)
generation_time
75397
tokens_prompt
77
tokens_completion
1047
native_tokens_prompt
66
native_tokens_completion
4582
native_tokens_completion_images
0
native_tokens_reasoning
4224
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
0.0459025
router
(null)
provider_responses
0
id
"resp_01ec0e1e9969ad730169931dc0349881949faa6e45d49fe8bc"
status
200
is_byok
false
latency
130
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771249088-HwtxZUs8vaI1FalmSgIG"
upstream_id
"resp_01ec0e1e9969ad730169931dc0349881949faa6e45d49fe8bc"
total_cost
0.0459025
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
100
100.0000%