NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09CVKG6RP16YBGYJZ6W0FV
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.2s
Cost:
$0.001381
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.63%
Dialogue to Total Word Ratio
(details)
40.9528%
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 crouched behind the bakery van, watching the townhouse glow with balloons and fairy lights. Through the curtains came shrieks of delight, the thump of tiny feet, and the merciless warbling of a karaoke machine. “That is a lot of joy,” she whispered. Bill adjusted his black gloves and peered around the corner. “Joy means gifts,” he said. “Gifts mean haul.” A clown in sequins lurched past the front door carrying a tray of juice boxes like a royal footman. Bill frowned. “Why is there a clown?” Molly checked her list, which was mostly doodles and one excellent reminder to bring rope. “Because it’s a children’s party, Bill.” He nodded gravely. “Right. Horrible venue choice.” They slipped through the side gate, stepping over a sprinkler shaped like a dinosaur. Inside the kitchen, a mountain of wrapping paper rustled in the heat. Molly pointed to the pile of presents stacked like a tiny department store. “Easy,” she breathed. “We take the lot and vanish before the cake.” Bill rubbed his hands together. “And if anyone asks?” Molly smiled. “We are the aunt and uncle.” From the hall, a child shouted, “The magician’s gone!” Bill froze. Molly listened to the delighted applause outside. “Perfect,” she said. “Everyone’s distracted.” Then the presents began to hum.
created_at
"2026-03-18T10:55:51.933Z"
3/18/2026, 10:55:51 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
394
moderation_latency
(null)
generation_time
2008
tokens_prompt
77
tokens_completion
345
native_tokens_prompt
66
native_tokens_completion
296
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
0.0013815
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_026a65be1ae5540d0169ba84b814608190b572f5d87a9801b6"
is_byok
false
latency
272
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-1773831351-gxWPJufn4DMXtIEyG4cV"
upstream_id
"resp_026a65be1ae5540d0169ba84b814608190b572f5d87a9801b6"
total_cost
0.0013815
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
0.63%
Dialogue to Total Word Ratio
Ratio: 25.00%, Deviation: 15.00%
neededClean
false
wordsTotal
212
wordsDialogue
53
40.9528%