NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09DTHX3RSS6VZ224MED8CD
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.9s
Cost:
$0.007502
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
45.76%
Dialogue to Total Word Ratio
(details)
72.8804%
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
“Tell me again why we’re dressed as clowns,” Molly whispered, tugging at her oversized shoe. “Because,” Bill said, adjusting his red nose, “no one ever suspects a clown of emotional distress.” “That is not a plan.” “It is a vibe.” “A vibe doesn’t open a locked door.” “I was hoping the door would open from embarrassment.” Molly sighed. “We are not here to embarrass a door. We’re here to steal presents.” “Right,” Bill said. “From a children’s party.” “Yes.” “With balloons?” “Bill.” “With cake?” “Bill.” “With a bouncy castle?” “The presents, Bill.” “Fine,” he muttered. “But I’m still calling it the Great Gift Liberation.” “Call it whatever you want after we’re gone.” “Do we have a getaway?” Molly pointed to a tiny scooter. “That?” “It’s eco-friendly.” “It’s also heartbreaking.” “Can you ride it or not?” “I can ride anything with enough panic.” “Good. Then smile like you belong here.” Bill grinned at the window full of streamers. “Molly?” “What?” “If anyone asks, I’m the magician.” “You?” “Yes.” “You can’t make anything disappear.” Bill winked. “Exactly.” Molly stared. “You’re impossible.” “Then let’s hope,” Bill said, “that the parents are as distracted by frosting as I am by legally questionable sparkle today.”
created_at
"2026-03-18T10:56:23.624Z"
3/18/2026, 10:56:23 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9331
moderation_latency
(null)
generation_time
9680
tokens_prompt
77
tokens_completion
716
native_tokens_prompt
66
native_tokens_completion
1656
native_tokens_completion_images
0
native_tokens_reasoning
1338
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
0.0075015
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0a8276cc456b7d440169ba84d7b0588194af4e4fb9f536d90a"
is_byok
false
latency
249
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-1773831383-1zA6STqp1kUD86VaZeJz"
upstream_id
"resp_0a8276cc456b7d440169ba84d7b0588194af4e4fb9f536d90a"
total_cost
0.0075015
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
45.76%
Dialogue to Total Word Ratio
Ratio: 80.60%, Deviation: 9.40%
neededClean
false
wordsTotal
201
wordsDialogue
162
72.8804%