NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07WVHHQSEFN6K06KHNT7NV
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.0s
Cost:
$0.006021
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
19.73%
Dialogue to Total Word Ratio
(details)
59.8642%
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 stitched the alley behind Marigold Hall, where the children’s party glowed like a spilled jar of marbles. Molly flattened the blueprint on a milk crate and jabbed at the service entrance. “Easy,” she whispered. Bill, wearing a fake mustache that looked alarmed, peered through the rain. “Easy is how we got the clown gig.” Inside, balloons bobbed against the windows, and a table of presents sat under a banner reading HAPPY BIRTHDAY, TREVOR! Molly smiled. “We slip in as entertainers, swap the gifts for decoys, and vanish before cake.” Bill frowned. “Decoys?” “Pillowcases stuffed with phone books.” “Brilliant,” he said. “Cruel to the books, though.” A siren wailed somewhere distant, and both thieves froze. Then the music inside swelled into a trumpet blast, masking the sound of their nerves. Molly straightened her gloves, already imagining the loot stacked in their van. Bill tipped his hat to the rain and grinned despite himself. “If anyone asks,” he said, “we’re the face-painting duo.” Molly laughed softly, and together they slipped toward the kitchen door, professional, cheerful, and utterly unfit for childcare. Behind them, the clown practice trumpet squealed, and Trevor’s grandmother applauded their stealth from a folding chair, mistaking everything for theater.
created_at
"2026-03-18T10:29:39.008Z"
3/18/2026, 10:29:39 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8515
moderation_latency
(null)
generation_time
8819
tokens_prompt
77
tokens_completion
468
native_tokens_prompt
66
native_tokens_completion
1327
native_tokens_completion_images
0
native_tokens_reasoning
1034
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
0.006021
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_024c60084a68e9750169ba7e9310288196bab2b510f9ee6945"
is_byok
false
latency
185
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-1773829779-Dq9sR1NySbIZ8TjeK0cv"
upstream_id
"resp_024c60084a68e9750169ba7e9310288196bab2b510f9ee6945"
total_cost
0.006021
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
19.73%
Dialogue to Total Word Ratio
Ratio: 21.29%, Deviation: 11.29%
neededClean
false
wordsTotal
202
wordsDialogue
43
59.8642%