NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1HYFSCRSH6RV50M95HK2B2
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.1s
Cost:
$0.004830
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
27.65%
Dialogue to Total Word Ratio
(details)
60.6494%
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 crouched behind the bouncy castle van, studying the suburban garden as balloons bobbed like cheerful sentries over the fence. Bill knelt beside her, wearing a caterer’s apron that still said KISS THE COOK in violent pink. “Tell me again,” Bill whispered, “why we’re robbing a six-year-old?” “We’re not robbing a six-year-old,” Molly said. “We’re liberating consumer goods from a chaotic gift pile.” “That sounds worse in a nicer accent.” “Focus. Three o’clock, the magician distracts the adults. Three-oh-two, you waddle in with the cupcake tray.” “I do not waddle.” “You absolutely waddle under pressure.” From the garden came a shriek of delighted children and the wet thump of a collapsed inflatable dinosaur. Bill peeked over the fence. “There are at least twelve of them. Sticky, unpredictable, sugar-powered. I’d rather burgle a bank.” “Banks have cameras. Children have face paint.” “And parents.” “Parents are useless near hired entertainment. It’s scientific.” Bill adjusted his paper hat. “What if they ask which child we belong to?” “Say ‘Olivia.’ There’s always an Olivia.” “And if there isn’t?” Molly grinned, producing a roll of gift tags. “Then in five minutes there will be.” Bill stared. “You scare me.” “Good,” she said, rising as applause erupted. “Now smile like you brought joy, not felony.”
created_at
"2026-03-06T12:28:50.867Z"
3/6/2026, 12:28:50 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
463
moderation_latency
(null)
generation_time
10088
tokens_prompt
77
tokens_completion
396
native_tokens_prompt
66
native_tokens_completion
311
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
0.00483
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_07699f793f6e5bcf0169aac882ef0881958100587b88834126"
is_byok
false
latency
175
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-1772800130-HuhvYcniqWsv4JRyoZKa"
upstream_id
"resp_07699f793f6e5bcf0169aac882ef0881958100587b88834126"
total_cost
0.00483
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
27.65%
Dialogue to Total Word Ratio
Ratio: 60.65%, Deviation: 10.65%
neededClean
false
wordsTotal
216
wordsDialogue
131
60.6494%