NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08KKXANTEMY8XYNM6QRXJB
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.6s
Cost:
$0.001453
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
11.32%
Dialogue to Total Word Ratio
(details)
43.2361%
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 bakery van, peering at the bungalow strung with paper lanterns and balloons. “You’re sure this is the right house?” Bill adjusted his black gloves. “The right house, the wrong morals. Yes.” “Excellent,” Molly said. “I brought lock picks, a flashlight, and a moral compass I can ignore.” From inside came the shriek of children, then a burst of tinny party music. Bill winced. “That sound alone should count as a security system.” “Makes the job easier,” Molly whispered. “They’ll be too busy frosting each other to notice us.” Bill lifted a brow. “That is a sentence no professional should ever say.” A clown-shaped sign read Happy Birthday, Tilly! “The presents are in the conservatory,” Molly said. “According to my contact.” “You have contacts now?” “I have standards. And a cousin who dates a balloon artist.” Bill leaned closer to the window. A mountain of wrapped gifts glowed beneath streamers. “That’s a lot of loot for one small criminal operation.” “Think of the resale value,” Molly said. “Think of the ribbons.” “Why the ribbons?” “Because,” she said, grinning, “we’re not monsters.” Bill sighed. “Fine. We go in quiet, grab the presents, and leave before anyone cries.” A child shouted, “Mum, the magician made the hamster disappear!” Molly stood. “Too late.”
created_at
"2026-03-18T10:42:04.855Z"
3/18/2026, 10:42:04 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
939
moderation_latency
(null)
generation_time
2409
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
66
native_tokens_completion
312
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
0.0014535
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0c41eda962fad4d20169ba817ceb4c81979193d8bc1bf191eb"
is_byok
false
latency
288
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-1773830524-95ZyW1weSK58m8MZWmQ6"
upstream_id
"resp_0c41eda962fad4d20169ba817ceb4c81979193d8bc1bf191eb"
total_cost
0.0014535
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
213
11.32%
Dialogue to Total Word Ratio
Ratio: 62.15%, Deviation: 12.15%
neededClean
false
wordsTotal
214
wordsDialogue
133
43.2361%