NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKANFAT3YTGNV2YY73GR70S
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 10s
Cost:
$0.003050
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
Night air smelled like popcorn. A neon 'Happy Birthday' sign flickered above them. A distant siren hummed, oddly festive tonight. Molly: We could slip in when the cake sings, nobody notices a whisper or shadow Bill: Perfect timing, Molly; I bring a ruler and a bag shaped like marshmallow tonight Molly: The presents are glittering targets, but the party favors may squeak, alerting teachers nearby Bill: Then we practice silent cartwheels and pretend we're stagehands carrying oversized helium balloons tonight Molly: We'll map exits with crayons, priceless kindness, and a napkin trail for decoy suspects Bill: Decoy suspects won't help if the confetti cannon misfires and ambushes the janitor accidentally Molly: I'll wear oven mitts; the frostings of secrets may melt before alarms do tonight Bill: If patrols wander, we improvise a lullaby and blend with a balloon-animal chorus nearby Molly: Our biggest risk is giving grandma glitter allergies; she sneezes and distances the operation Bill: Then we switch to cupcake camouflage, nibble sample, and vanish before the frosting dries Molly: If we fail, we blame the cake and open a gift-wrapping consultancy for trainees Bill: Deal; until then, we rehearse our stealth in the sandbox and keep smiling together
created_at
"2026-02-16T13:37:43.033422+00:00"
2/16/2026, 1:37:43 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6920
moderation_latency
(null)
generation_time
70287
tokens_prompt
77
tokens_completion
1595
native_tokens_prompt
66
native_tokens_completion
7617
native_tokens_completion_images
0
native_tokens_reasoning
7296
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
0.0030501
router
(null)
provider_responses
0
id
"resp_061cd21ac98948920169931d5fa6848197ad462e9ce7ce1408"
status
200
is_byok
false
latency
127
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248991-3D5YEaSbV6Jy8FPKJM11"
upstream_id
"resp_061cd21ac98948920169931d5fa6848197ad462e9ce7ce1408"
total_cost
0.0030501
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
0.0000%
Dialogue to Total Word Ratio
Ratio: 2.97%, Deviation: 87.03%
neededClean
false
wordsTotal
202
wordsDialogue
6
49.9920%