NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAGHRY9SNWQ16SNJKQYNWB
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 17s
Cost:
$0.005823
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
Tonight's children's party was a toy-strewn carnival of cheerful danger. Molly checked the map on the back of a dessert napkin, which smelled faintly of lemon and rebellion. Bill adjusted his mask, which kept slipping, like a stubborn idea. They whispered in the pantry where the glitter from last year's balloon drop still lingered. The plan was simple: enter as clowns, collect the loot, exit through the kitchen window, and vanish before the cake trucks learned their names. Molly rehearsed the slogan she'd use to calm any suspicious grown-ups: 'We are here for happiness tax.' Bill grinned, then giggled loudly. Molly: Tonight the party is loud, bright, sugary, and suspiciously kind; we need a clownish cover, a recipe for mischief, and absolute nonchalance and stealth. Bill: We'll enter as balloon-throwing professionals, mingle with marshmallow fans, stall cameras with a chorus of giggles, and pretend to organize the cake line today. Molly: If we trip the lights, the party will glow with confetti; we'll glide between tables, collect presents with care, and leave through the door. Bill: Remember, we smile like hosts, not criminals; if a kid asks our names, we say we are the 'Joy Engineers' on temporary duty tonight.
created_at
"2026-02-16T13:36:07.461619+00:00"
2/16/2026, 1:36:07 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5664
moderation_latency
(null)
generation_time
136461
tokens_prompt
77
tokens_completion
1780
native_tokens_prompt
66
native_tokens_completion
14549
native_tokens_completion_images
0
native_tokens_reasoning
14272
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
0.0058229
router
(null)
provider_responses
0
id
"resp_091b9994c3e1f7fb0169931cbe502c81939b13c507e6d196d2"
status
200
is_byok
false
latency
143
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248830-mE9Efhi1KmGi8StDHy3k"
upstream_id
"resp_091b9994c3e1f7fb0169931cbe502c81939b13c507e6d196d2"
total_cost
0.0058229
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9190%
Matches word count
n/a
neededClean
false
words
203
0.0000%
Dialogue to Total Word Ratio
Ratio: 8.37%, Deviation: 41.63%
neededClean
false
wordsTotal
203
wordsDialogue
17
49.9595%