NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM094DHB0SET2932J862QTY8
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.2s
Cost:
$0.001643
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
Overall
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
Molly peered through the bakery window at the birthday hall across the street. “There it is, Bill. Balloons, streamers, tiny paper hats. The mother lode.” Bill adjusted his tie, which was really a length of ribbon. “You say that about every room with cake.” “Because cake is a treasure map.” “We’re here for the presents.” “Exactly. A room full of brightly wrapped loot, waiting for us to liberate it.” Bill frowned. “Liberate is what you call theft when you’re trying to sound philanthropic.” “Then stop objecting and start thinking.” Molly pointed at the entrance. “One clown. Two parents. A bowl of punch. Weak security.” “Children?” “They’re five. They’ll be distracted by sugar and chaos.” Bill leaned closer. “And our exit?” “Melt into the party, mingle, congratulate the birthday boy, and leave carrying the gifts like we belong there.” “We don’t belong there.” “Moral flexibility, Bill. It’s our brand.” He sighed. “Fine. But if anyone asks, I’m the uncle.” Molly grinned. “Perfect. I’ll be the aunt who shows up late and leaves with the flat-screen.”
created_at
"2026-03-18T10:51:15.382Z"
3/18/2026, 10:51:15 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
993
moderation_latency
(null)
generation_time
2098
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
66
native_tokens_completion
354
native_tokens_completion_images
0
native_tokens_reasoning
85
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
0.0016425
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_03cb86f7ff865ab00169ba83a374e4819797c4a1e451e112f2"
is_byok
false
latency
233
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-1773831075-n2K9DJNuL3UwCYQfk7Pz"
upstream_id
"resp_03cb86f7ff865ab00169ba83a374e4819797c4a1e451e112f2"
total_cost
0.0016425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
1.04%
Matches word count
n/a
neededClean
false
words
174
0.00%
Dialogue to Total Word Ratio
Ratio: 78.29%, Deviation: 28.29%
neededClean
false
wordsTotal
175
wordsDialogue
137
0.5180%