NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QJNWN2XE19HCX54AHMMGE
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
34.5s
Cost:
$0.021975
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.54%
Dialogue to Total Word Ratio
(details)
99.7682%
Overall
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
“Children’s parties,” said Molly, “are basically tiny banks with frosting.” “Banks don’t sing at you,” Bill said. “Exactly why nobody suspects a robbery.” “We’re robbing seven-year-olds, Mol.” “We’re liberating unappreciated plastic from sticky custody.” “Sticky custody is still custody.” “Listen. Balloon arch at the front, magician in the garden, sugar crash by three. We go in as face painters, sweep the gift table, and vanish before the clown starts making poodles.” “I hate clowns. They fold judgment into balloons.” “Focus. You distract the mums with your tragic moustache.” “It’s not tragic; it’s continental.” “It’s trembling.” “That’s strategy. It says, ‘Trust me, I know glitter.’” Bill adjusted his clip-on bow tie. “What about the children?” he asked. “Easy. Promise temporary tattoos. Nothing clears a room faster than a paper tiger and parental regret.” “And the presents?” “Into the pram.” “The giant pink pram?” “No one searches a giant pink pram, Bill. That’s law.” “What if the birthday boy notices?” “Then we hand him a kazoo and point at the cake.” “You’ve done this before.” “Professionally? Never. Socially? Twice.” “That explains the confetti in your shoes.” “Also,” said Molly, “if things go wrong, cry and say you’re the magician’s accountants. From Belgium.”
created_at
"2026-03-09T16:41:10.82Z"
3/9/2026, 4:41:10 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
27653
moderation_latency
(null)
generation_time
34322
tokens_prompt
77
tokens_completion
618
native_tokens_prompt
66
native_tokens_completion
1454
native_tokens_completion_images
0
native_tokens_reasoning
1150
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
0.021975
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_045d8510a253fca60169aef826e5b48190aaf3ddfacbeb07f5"
is_byok
false
latency
187
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773074470-8kgUcKXWXGbTWJUFc3Df"
upstream_id
"resp_045d8510a253fca60169aef826e5b48190aaf3ddfacbeb07f5"
total_cost
0.021975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
99.54%
Dialogue to Total Word Ratio
Ratio: 92.61%, Deviation: 2.61%
neededClean
false
wordsTotal
203
wordsDialogue
188
99.7682%