NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08SEYHFHT7DAP6PZBWN8H5
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.0s
Cost:
$0.001404
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
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
Molly and Bill crouched behind the hedge across from number 14, where balloons bobbed above the fence like cheerful sentries and a clown car was presumably a purely decorative threat. Through the front window they could see parents laughing, children shrieking, and a tower of wrapped presents stacked beneath a paper banner that read HAPPY BIRTHDAY TILLY in glittering purple. Bill adjusted his black cap and squinted. “Too many witnesses,” he muttered. Molly, who had brought a clipboard, a false mustache, and a flute full of orange juice, nodded with professional gravity. “Good. No one suspects the caterers.” A small boy in a superhero mask raced past the curtains with an armful of jelly sweets, nearly ruining Bill’s resolve. “I hate parties,” he said. “Too much joy. It makes me itchy.” Molly checked her watch. “We go in with the cake delivery, blend with the balloons, and exfiltrate via the bouncy castle.” “You really think they’ll buy it?” “They already hired a magician,” she said. “Standards are low.” Inside, the birthday song began, wobbling through the warm air like an injured bird. Bill grinned despite himself. “Right then,” he said, “let’s steal Christmas in miniature.” Molly straightened her tie. “To the presents,” she whispered, “and may the party bags never identify us.”
created_at
"2026-03-18T10:45:16.383Z"
3/18/2026, 10:45:16 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
426
moderation_latency
(null)
generation_time
1902
tokens_prompt
77
tokens_completion
356
native_tokens_prompt
66
native_tokens_completion
301
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.001404
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0f15b161b6cd17700169ba823c727881939fab9df12fac2783"
is_byok
false
latency
208
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-1773830716-PTonpRXlqDanb7PdJbQp"
upstream_id
"resp_0f15b161b6cd17700169ba823c727881939fab9df12fac2783"
total_cost
0.001404
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
0.00%
Dialogue to Total Word Ratio
Ratio: 32.08%, Deviation: 22.08%
neededClean
false
wordsTotal
212
wordsDialogue
68
40.6364%