NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HHE3B524DTEDJ31G84HS6
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.7s
Cost:
$0.004680
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
99.71%
Dialogue to Total Word Ratio
(details)
83.9043%
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 of Number Twelve, staring at a garden festooned with balloons, bunting, and a cardboard pirate ship listing gently over the paddling pool. Children shrieked in sugar-hazed circles while a clown on stilts folded balloon swords with the solemnity of a cathedral organist. Near the patio doors, a mountainous table sagged under frosted cake, orange squash, and a glittering hill of wrapped presents. “Timing,” Molly whispered, flattening her cap. “We go in with the magician.” Bill adjusted his too-small waistcoat and peered through the leaves. “I still say the clown has better cover.” The scent of sausages drifted over the fence, almost enough to derail professional ambition. Molly unfolded a hand-drawn plan on the back of a takeaway menu: gate, shed, patio, loot, retreat. Bill nodded gravely, though his eyes kept wandering to the cake shaped like a dragon wearing sunglasses. A hired princess swept across the lawn, trailed by children demanding stickers and justice. Parents laughed into paper cups, blissfully inattentive. The pile of presents glimmered like buried treasure brought irresponsibly aboveground. “On my mark,” Molly said. Bill swallowed. “If a six-year-old interrogates me, I’m folding.” Molly patted the sack, checked the gate latch, and smiled the smile of a woman about to commit something deeply unserious.
created_at
"2026-03-06T12:21:43.154Z"
3/6/2026, 12:21:43 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
421
moderation_latency
(null)
generation_time
8616
tokens_prompt
77
tokens_completion
364
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
0.00468
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0c5aba1381a525630169aac6d7378c8195b5031837c785c80b"
is_byok
false
latency
145
model_permaslug
"openai/gpt-5.4-20260305"
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-1772799703-ppx95emsoAsAM21ztSr6"
upstream_id
"resp_0c5aba1381a525630169aac6d7378c8195b5031837c785c80b"
total_cost
0.00468
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
214
99.71%
Dialogue to Total Word Ratio
Ratio: 12.33%, Deviation: 2.33%
neededClean
false
wordsTotal
219
wordsDialogue
27
83.9043%