NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM084Z78TW3A1XHZMX9SNK8Z
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.2s
Cost:
$0.001467
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5011%
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 hedge, staring at the pastel explosion of balloons and streamers spilling out of Mrs. Pritchard’s garden. Children shrieked with sugar-fueled joy while a clown on stilts wobbled near the cake table, apparently held together by helium and optimism. Bill adjusted his black gloves, which were so cheap they squeaked. “Simple job,” he whispered. “We slip in, grab the presents, and vanish.” Molly eyed the gift mountain by the conservatory. “You say that every time.” “And every time, we’re in and out before anyone knows.” “Last time,” she said, “we were chased by a miniature pirate on a tricycle.” Bill frowned. “That was a fluke.” A tiny voice suddenly shouted, “The piñata’s gone missing!” and the crowd surged toward the back lawn. The two thieves froze as a toddler in a fairy costume waddled past dragging a ribbon wand like a sabre. Molly grinned. “Perfect distraction.” Bill gave the gazebo a quick look. “You take the left side. I’ll cover the presents.” “And if there’s a saxophone?” He winced. “We never speak of the saxophone.” Together they slipped through the roses, blending into the chaos of cake, confetti, and laughter, two professionals on a mission only slightly complicated by the fact that the party’s security consisted of a confused bouncy castle and seventeen sugar-high seven-year-olds.
created_at
"2026-03-18T10:34:04.914Z"
3/18/2026, 10:34:04 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
373
moderation_latency
(null)
generation_time
2020
tokens_prompt
77
tokens_completion
377
native_tokens_prompt
66
native_tokens_completion
315
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
0.001467
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0dc114b1223904750169ba7f9cf6b0819384c906b2293194ee"
is_byok
false
latency
164
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-1773830044-VFinBBqBSqsVjvkdXvOj"
upstream_id
"resp_0dc114b1223904750169ba7f9cf6b0819384c906b2293194ee"
total_cost
0.001467
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
218
0.00%
Dialogue to Total Word Ratio
Ratio: 30.18%, Deviation: 20.18%
neededClean
false
wordsTotal
222
wordsDialogue
67
17.5011%