NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A70RW4049D840MPV4WVXG
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
11.1s
Cost:
$0.014040
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
53.31%
Dialogue to Total Word Ratio
(details)
76.6571%
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 hedges, peering at the suburban garden where balloons shivered in the dusk like nervous fish. Inside, a banner announced HAPPY BIRTHDAY, LUCY! and the back door was propped open by a fire truck toy. Bill adjusted his knit cap, which had a pom-pom because, as he said, “Intimidation is overrated.” “Last chance to quit?” Molly whispered. Bill checked the clipboard they’d stolen. “We’re professionals.” “Professional what?” “Disappointments.” Laughter drifted from the party, followed by a recorder squeal and applause. Molly watched a clown bend a balloon sword for a child in a paper crown. Presents stacked beside the cake table, shiny and square, fat with possibility. Bill smiled. “We take the gifts, leave the fruitcake, and vanish.” “Manners?” “Only in emergencies.” They slipped through the side gate, past a sleeping Labrador wearing party hats taped to its ears. Molly tested the porch handle. Unlocked. “Too easy,” she murmured. Bill grinned. “That’s how legends begin.” From inside came a shriek of delight. Molly winced. “We should hurry before someone learns sharing.” Bill nodded, and together they eased slowly into the hall, where the presents waited like treasure, wrapped in paper loud enough to shame a brass band.
created_at
"2026-03-18T11:10:09.19Z"
3/18/2026, 11:10:09 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10079
moderation_latency
(null)
generation_time
10576
tokens_prompt
77
tokens_completion
344
native_tokens_prompt
66
native_tokens_completion
3109
native_tokens_completion_images
0
native_tokens_reasoning
2821
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
0.01404
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_00782bd376ee79d20169ba881143088194923e134c98a0d6bb"
is_byok
false
latency
211
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-1773832209-rdOTl61ZAgYtGxA4uyPj"
upstream_id
"resp_00782bd376ee79d20169ba881143088194923e134c98a0d6bb"
total_cost
0.01404
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
200
53.31%
Dialogue to Total Word Ratio
Ratio: 18.91%, Deviation: 8.91%
neededClean
false
wordsTotal
201
wordsDialogue
38
76.6571%