NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9PV6E34H0726DG136B8XFN
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
26.9s
Cost:
$0.021675
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
97.47%
Dialogue to Total Word Ratio
(details)
98.7362%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 hedge at the bouncing castle, where shrieking children orbited a table piled with presents like gulls around chips. “Bill, tell me that’s not a clown on stilts.” “It is, and I refuse to be intimidated by a man in striped socks.” “You said that about the mall cop.” “He had a Segway, Molly. That’s cavalry.” “Focus. Entry points?” “Front gate disguised as responsible relatives, or back fence disguised as highly athletic shrubs.” “We’ve never been athletic shrubs.” “We’ve been worse. Remember the aquarium job?” “I still smell haddock when I’m nervous. What about the dog?” “Bribed with sausage rolls.” “The magician?” “Easily distracted by mirrors.” “The children?” “Sticky, short, and unpredictable. We avoid them like taxes.” “And the presents?” “Snatch, stack, and vanish before cake.” “What if they sing?” “Happy Birthday?” “No, the alarm. Kids always sing before chaos.” “Then we move on the second ‘to you.’” “Bill, one more issue. That piñata is looking at me.” “Everything looks at you when you owe it money.” Molly straightened her hat and grinned. “Right. We go in smiling, leave jingling, and under no circumstances accept face paint.” “Agreed. Last time the getaway horse laughed all the way.”
created_at
"2026-03-09T16:28:21.327Z"
3/9/2026, 4:28:21 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
25726
moderation_latency
(null)
generation_time
26597
tokens_prompt
77
tokens_completion
394
native_tokens_prompt
66
native_tokens_completion
1434
native_tokens_completion_images
0
native_tokens_reasoning
1140
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
0.021675
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0620694b4cd566740169aef5256a808196899d8ed55cb882c4"
is_byok
false
latency
169
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-1773073701-woU24YXDeMA7nq3SVSCX"
upstream_id
"resp_0620694b4cd566740169aef5256a808196899d8ed55cb882c4"
total_cost
0.021675
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
97.47%
Dialogue to Total Word Ratio
Ratio: 86.00%, Deviation: 4.00%
neededClean
false
wordsTotal
200
wordsDialogue
172
98.7362%