NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AP7GBXKN2BHSWG39Q2NGK
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.2s
Cost:
$0.005846
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9933%
Overall
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
Rain slicked the alley behind the community hall, where Molly and Bill crouched beside a catering cart that smelled faintly of frosting and defeat. Through the frosted windows they could see balloons, paper crowns, and a chaos of tiny feet circling the gift table like raccoons around a trash can. “Worth it?” Molly whispered. “Absolutely,” Bill said. “Kids never inventory the glitter.” “And the parents?” “Distracted by juice boxes and competitive smiling.” Bill adjusted his tie, a criminally good one, and opened the envelope of invitations he'd stolen from the recycling bin. The plan was elegant in the way only terrible plans could be: he would deliver a fake magician's message, Molly would roll in a cart marked EXTRA NAPKINS, and together they'd swap the real presents for identical empty boxes they had packed with old newspapers and one deeply insulting banana. Unfortunately, the hall door was guarded by a volunteer clown with a clipboard and the haunted stare of a woman who had seen too many pinatas. Molly peered at the clown and sighed. “You handle the banana,” she said. Bill grinned, already in motion, because every great robbery begins with a bad idea and excellent timing indeed.
created_at
"2026-03-18T11:18:27.609Z"
3/18/2026, 11:18:27 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9668
moderation_latency
(null)
generation_time
9962
tokens_prompt
77
tokens_completion
788
native_tokens_prompt
66
native_tokens_completion
1288
native_tokens_completion_images
0
native_tokens_reasoning
1034
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
0.0058455
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0029c92da15b3c310169ba8a03aaf081908ee6350fd1d44a09"
is_byok
false
latency
199
model_permaslug
"openai/gpt-5.4-mini-20260317"
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-1773832707-9WZBoz7BjlV4ccnJ3AOV"
upstream_id
"resp_0029c92da15b3c310169ba8a03aaf081908ee6350fd1d44a09"
total_cost
0.0058455
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
199
99.99%
Dialogue to Total Word Ratio
Ratio: 11.06%, Deviation: 1.06%
neededClean
false
wordsTotal
199
wordsDialogue
22
99.9933%