NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07EFDCN52WJKS9WET9YYJT
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
23.0s
Cost:
$0.026231
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
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 hedges while the birthday house glittered with paper stars and vanilla from the kitchen. Inside, children shrieked at a magician whose rabbit kept trying to escape through his collar. Bill raised his toolkit: a spoon, a wire, and a face of saintly concern. "We blend in, Molly." "Like parents, or clowns?" "Parents, but quieter." Molly tucked a folding ladder beneath her coat and pointed at the side gate. "Focus." They slipped through the side gate just as a toddler in a cape declared himself king of the cake. Molly palmed the lock with her spoon while Bill distracted a poodle wearing sunglasses and a sash. "I prefer louder theft." The presents gleamed beneath the tree, wrapped so beautifully they looked too expensive to touch. Molly frowned at a box the size of a microwave and twice as noisy. "Shh." Bill whispered, "Excellent party taste." Molly nodded toward a stack labeled FROM GRANDMA, DO NOT SHAKE, which was exactly the sort of warning she respected. "Apparently." Bill hefted the sack and grinned as the magician applauded his own disappearing rabbit. When the parents turned back, Molly and Bill were over the fence, with glittering loot.
created_at
"2026-03-18T10:21:47.831Z"
3/18/2026, 10:21:47 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
22558
moderation_latency
(null)
generation_time
22865
tokens_prompt
77
tokens_completion
558
native_tokens_prompt
66
native_tokens_completion
5818
native_tokens_completion_images
0
native_tokens_reasoning
5554
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
0.0262305
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0844fc3d921ad59c0169ba7cbbe5cc819499dccf2334becd14"
is_byok
false
latency
203
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-1773829307-SuKOKDTGGZWGs7zOC6TA"
upstream_id
"resp_0844fc3d921ad59c0169ba7cbbe5cc819499dccf2334becd14"
total_cost
0.0262305
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
100.00%
Dialogue to Total Word Ratio
Ratio: 10.50%, Deviation: 0.50%
neededClean
false
wordsTotal
200
wordsDialogue
21
99.9997%