NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08GEWCW9VBD6YD4BHAMNH9
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.8s
Cost:
$0.001597
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
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 balloon arch and stared at the gift table through the catering tent flap. “Bill, remind me why we’re robbing a five-year-old’s birthday party.” Bill adjusted his fake mustache. “Because, Molly, the loot is abundant, the security is asleep, and the victim has been distracted by a clown with a foam sword.” She winced as a child shrieked with joy. “You make it sound noble.” “It is noble,” Bill said. “We’re redistributing presents from one extremely fortunate child to two extremely underpaid professionals.” Molly peeked at the stacked boxes. “I see a train set, three dolls, and something shaped like a volcano.” “Excellent,” Bill said. “Volcanoes are always premium.” “Bill, the parents are right there.” “Then we keep it classy. We wait for the magician to do the rabbit trick, the music to get loud, and the grandparents to start dancing.” Molly held up a tiny crowbar. “And then?” “And then,” Bill whispered, “we enter the Bounce House Exit Strategy.” She frowned. “That’s not a strategy.” “It is if nobody can catch us while we’re still in the bounce house.” Molly grinned despite herself. “Fine. But if we’re doing this, I’m taking the dinosaur wrapping paper.” “Deal,” Bill said. “Now act casual. You look suspiciously like a mastermind.”
created_at
"2026-03-18T10:40:21.402Z"
3/18/2026, 10:40:21 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2280
moderation_latency
(null)
generation_time
2599
tokens_prompt
77
tokens_completion
498
native_tokens_prompt
66
native_tokens_completion
344
native_tokens_completion_images
0
native_tokens_reasoning
42
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
0.0015975
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0f811727db85176a0169ba81157374819585c3f22f6f87b54f"
is_byok
false
latency
173
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-1773830421-hbJwbGp8q1Kh6R9fCBx7"
upstream_id
"resp_0f811727db85176a0169ba81157374819585c3f22f6f87b54f"
total_cost
0.0015975
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
0.00%
Dialogue to Total Word Ratio
Ratio: 73.71%, Deviation: 23.71%
neededClean
false
wordsTotal
213
wordsDialogue
157
43.1902%