NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09R092ZT3RE6J4T4BXNFSY
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.0s
Cost:
$0.001881
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
3.42%
Dialogue to Total Word Ratio
(details)
4.7536%
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 rainbow of balloons drifting over the backyard next door. “Bill, tell me again why we’re robbing a party for six-year-olds.” “Because,” Bill said, adjusting his tie, “children receive gifts with terrible vigilance and zero tax documentation.” “That is not a real reason.” “It is for me.” Molly watched a clown twist a balloon into something alarming. “We’re going to look ridiculous.” “We are thieves, Molly. Ridiculous is our brand.” “They’ll notice us.” “Not if we blend in.” “With what? Tiny hats?” “Exactly. Tiny hats, big confidence.” Molly sighed and tugged at the paper crown he’d made from a cereal box. “If anyone asks, I’m not carrying a sack.” “You’re carrying an investment portfolio.” “That sack is shaped like a football.” “Artisanal portfolio.” A child’s laughter burst from the yard, followed by the thump of a piñata missing its moral center. Molly winced. “I hate that you make crime sound like party planning.” Bill grinned. “Same skill set. Same snacks. Now, on my mark, we enter boldly, compliment the cake, and gently liberate the presents.” “And if they stop us?” Bill winked. “Then we were never here.” From the backyard came a cry of, “The treasure hunt starts now!” Molly adjusted her tiny hat. “Bill?” “Yes?” “I’m beginning to think the children are stealing from us.”
created_at
"2026-03-18T11:01:57.168Z"
3/18/2026, 11:01:57 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1622
moderation_latency
(null)
generation_time
2518
tokens_prompt
77
tokens_completion
414
native_tokens_prompt
66
native_tokens_completion
407
native_tokens_completion_images
0
native_tokens_reasoning
90
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
0.001881
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0b0b31229287eb780169ba86254cd48196be9dd99e5b0b2372"
is_byok
false
latency
255
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-1773831717-RB1FTEy3bf12ATGqQqnX"
upstream_id
"resp_0b0b31229287eb780169ba86254cd48196be9dd99e5b0b2372"
total_cost
0.001881
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
223
3.42%
Dialogue to Total Word Ratio
Ratio: 63.56%, Deviation: 13.56%
neededClean
false
wordsTotal
225
wordsDialogue
143
4.7536%