NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07NQ2X3ZP210S7QEAJ4P8W
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.2s
Cost:
$0.001485
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
99.69%
Dialogue to Total Word Ratio
(details)
90.4819%
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
“Bill, if this goes wrong, I’m blaming your face,” Molly whispered, peering around the corner at the banner reading HAPPY BIRTHDAY, CAPTAIN SQUIRT. Bill adjusted his black beanie. “My face has a lot to answer for, but tonight it’s innocent.” “It’s a children’s party,” Molly said. “Why does it need three balloons shaped like tigers?” “Because children are rich in imagination and poor in security,” Bill said, tugging the sack over his shoulder. “Also, apparently, in supervision.” Molly watched a clown juggle beside a table of cupcakes. “We are stealing presents from toddlers.” “We are redistributing opportunities,” Bill said. “The gifts will go to a more appreciative audience.” “You mean us.” “I said appreciative.” A small boy in pirate dress staggered past them, carrying a sword the size of a baguette. “Excuse me,” he said brightly, “are you the entertainment?” Molly smiled with alarming tenderness. “Yes, dear.” Bill hissed, “Don’t bond with the target.” “I’m not bonding. I’m gathering intel.” From inside, a chorus roared, “Cake! Cake! Cake!” Bill lifted his sack. “Now, while they’re distracted.” Molly nodded. “On my count.” “Which count?” “The one after I’ve changed my mind,” she said, and they slipped through the door as the clown sneezed confetti and no one noticed the presents beginning to disappear.
created_at
"2026-03-18T10:25:45.065Z"
3/18/2026, 10:25:45 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
426
moderation_latency
(null)
generation_time
2098
tokens_prompt
77
tokens_completion
398
native_tokens_prompt
66
native_tokens_completion
319
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
0.001485
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_03074f37d61e48660169ba7da925f88193b2c4f9989d7f0668"
is_byok
false
latency
202
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-1773829545-WurMTPIv1TGVlQYn0nTo"
upstream_id
"resp_03074f37d61e48660169ba7da925f88193b2c4f9989d7f0668"
total_cost
0.001485
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
99.69%
Dialogue to Total Word Ratio
Ratio: 52.36%, Deviation: 2.36%
neededClean
false
wordsTotal
212
wordsDialogue
111
90.4819%