NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AKNG607EFERSZ3CWPD4EB
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.8s
Cost:
$0.008262
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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
Rain ticked the alley as Molly unfolded the party flyer like a treasure map. Through the frosting on the window, balloons bobbed over a sea of tiny shoes and sugar wreckage. Bill adjusted his gloves and peered at the stack of gifts waiting beside the cake table. “Easy,” he said. “They’ll never expect a strike from the clown cotillion.” Molly snorted. “We are not calling it that.” “Fine,” Bill whispered, “Operation Sticky Fingers.” She winced. “Still worse.” Inside, a magician was making a rabbit disappear and reappear in a cone hat, which Molly took as an omen. She cracked the service door. “Remember,” she said, “no noise.” Bill hefted an empty laundry sack. “Molly, I was born for silence.” A toddler screamed with delighted triumph. Bill froze. Molly sighed. “That’s not helping.” “I know,” he muttered. “But he seems to have spotted me.” The toddler pointed, then handed Bill a plastic crown. Bill stared, humbled. Molly grinned. “Excellent. You’re promoted to king of the loot.” “Do kings get ladders?” “Only if they’re practical.” Together they slipped between gift bags, tinsel, and a mountain of paper hats, while the band played a saxophone version of Happy Birthday. Bill whispered, “This is perfect.”
created_at
"2026-03-18T11:17:03.634Z"
3/18/2026, 11:17:03 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
12291
moderation_latency
(null)
generation_time
12618
tokens_prompt
77
tokens_completion
579
native_tokens_prompt
66
native_tokens_completion
1825
native_tokens_completion_images
0
native_tokens_reasoning
1537
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
0.008262
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0bbb209a091c30910169ba89afb47081959d89b4a68961eb29"
is_byok
false
latency
191
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-1773832623-cBLZ5VVDc35eCOxRT0qC"
upstream_id
"resp_0bbb209a091c30910169ba89afb47081959d89b4a68961eb29"
total_cost
0.008262
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
201
0.00%
Dialogue to Total Word Ratio
Ratio: 30.85%, Deviation: 20.85%
neededClean
false
wordsTotal
201
wordsDialogue
62
49.9995%