NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QD9FM506JKRPQ39660VDZ
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
28.5s
Cost:
$0.022080
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3940%
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, you cannot wear tap shoes to a burglary.” “They’re stealthy in spirit, Bill.” “Spirit clacks.” “Fine. I’ll tiptoe between clacks. Now, the children’s party starts at two, cake at three, sugar crash at four. We strike at gift o’clock.” “Gift o’clock isn’t a time.” “It is if you believe in yourself.” “I believe in disguises. Balloon artist?” “I look shifty with a poodle made of latex.” “You always look shifty.” “Compliment accepted. What’s your disguise?” “Magician. Cape, wand, tragic facial hair.” “You already own tragic facial hair.” “Thank you. While I distract them with a card trick, you sweep the presents into the bouncy castle.” “The getaway castle?” “Exactly. We bounce out.” “Bill, that is the worst plan since you tried tunneling into a bakery with a soup spoon.” “That spoon had ambition.” “And soup.” “Focus, Molly. Any obstacles?” “Clown.” “I fear no clown.” “You should. He does close-up balloons.” “Monstrous. Password?” “If anyone asks, we’re cousins.” “Whose cousins?” “Everyone’s. It’s a children’s party, Bill. Half the adults are confused already.” “And if we’re caught?” “We say we’re from the Surprise Redistribution Committee.” “Robin Hood for wrapping paper.” “Now you’re getting festive.” “And morally dubious, which completes the look.”
created_at
"2026-03-09T16:38:14.271Z"
3/9/2026, 4:38:14 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
25373
moderation_latency
(null)
generation_time
28344
tokens_prompt
77
tokens_completion
536
native_tokens_prompt
66
native_tokens_completion
1461
native_tokens_completion_images
0
native_tokens_reasoning
1151
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
0.02208
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0d10959580f9010d0169aef7765e3c8195be5617c8e780d613"
is_byok
false
latency
213
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-1773074294-aivUJkAUtqWmezviuEme"
upstream_id
"resp_0d10959580f9010d0169aef7765e3c8195be5617c8e780d613"
total_cost
0.02208
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
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
201
wordsDialogue
201
68.3940%