NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08KZ2K2ZC9S8VKTJ3CJYZP
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.3s
Cost:
$0.007132
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
93.71%
Dialogue to Total Word Ratio
(details)
96.7273%
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
Molly peered through the hedge. "There it is, Bill. The annual shriek-fest." Bill adjusted his tie. "You mean the children's party?" "That's what I said. Look at those presents." "Stacked like tiny, colorful regrets," Bill whispered. "Exactly. We go in, blend in, and leave with the loot." "Blend in?" Bill hissed. "I am a six-foot man in a fake mustache carrying a sack." "Then act like a clown." "I resent that." "Good. Resentment is subtle." Inside, a balloon popped. "Did you hear that?" "Yes," Molly said. "The room is full of sugar and panic. Perfect cover." Bill swallowed. "What if they ask questions?" "Children?" Molly scoffed. "Please. Tell them you're the magician." "I can't do magic." "Then do what every magician does: lie with confidence." "And the presents?" "We take the big ones first. Train set, dollhouse, anything that rattles." "Disgusting." "Bill, we are thieves." "Fair. But if I get caught by a toddler, I want it on my gravestone." Molly grinned. "Move quietly." Bill nodded. "And if there's cake?" "Bill." "What?" "No snacking. We're professionals." "Fine," he whispered, "but if there's blue frosting, I'm weak." Molly laughed. "Then don't look at the cake. Look at the exits and the emergency confetti. Now, move."
created_at
"2026-03-18T10:42:16.288Z"
3/18/2026, 10:42:16 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5453
moderation_latency
(null)
generation_time
6092
tokens_prompt
77
tokens_completion
333
native_tokens_prompt
66
native_tokens_completion
1574
native_tokens_completion_images
0
native_tokens_reasoning
1250
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
0.0071325
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_00a6ee27eb70a7fd0169ba818859c48197aba3130fddc1d99f"
is_byok
false
latency
184
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-1773830536-4gnUHYEUOSfPMy7dHJ4Q"
upstream_id
"resp_00a6ee27eb70a7fd0169ba818859c48197aba3130fddc1d99f"
total_cost
0.0071325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
93.71%
Dialogue to Total Word Ratio
Ratio: 84.95%, Deviation: 5.05%
neededClean
false
wordsTotal
206
wordsDialogue
175
96.7273%