NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07KNH9KSTZZZZ5A34642GT
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.2s
Cost:
$0.001602
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0001%
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 beside the fence, watching the bungalow glow with paper lanterns and bad judgment. Inside, children shrieked with the bliss of the recently sugar-fed, and somewhere a trumpet played a version of Happy Birthday that sounded like a duck being mugged. Bill adjusted his black cap, which was, unfortunately, made of sequins. “You sure this is the right house?” Molly rolled her eyes. “Bill, the giant balloon arch says HAPPY BIRTHDAY NED in twelve-foot letters. Unless Ned runs three parties a week, yes.” He peered through the hedge. “Looks crowded.” “That’s why it’s perfect. Nobody counts presents while being chased by small people with sticky hands.” Bill nodded, then frowned at the gift table visible through the kitchen window. “There’s a lot of wrapping paper.” “Focus,” Molly whispered. “We slip in through the side gate, mingle, smile, and lift the loot.” Bill blinked. “Mingle?” “Blend.” “With children?” “With confidence.” A door burst open, and a chorus of “Surprise!” exploded into the garden. Molly grabbed Bill’s sleeve. “Too late for subtlety.” “Good,” he said, straightening his cap. “I’m terrible at subtlety.” Inside, the presents sat beneath streamers, glittering like treasure. Molly grinned. “Remember the plan.” Bill grinned back. “Take the cake too?” “No, Bill.” “Because I can carry—” “No, Bill.” They stepped into the chaos, looking exactly like two adults who had definitely been invited and definitely had no idea what they were doing.
created_at
"2026-03-18T10:24:37.94Z"
3/18/2026, 10:24:37 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
321
moderation_latency
(null)
generation_time
2034
tokens_prompt
77
tokens_completion
435
native_tokens_prompt
66
native_tokens_completion
345
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
0.001602
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_098eebd35036f2630169ba7d66054881978d1eebc0224eda99"
is_byok
false
latency
215
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-1773829477-Yo67XoPdP1WXskWD3cw9"
upstream_id
"resp_098eebd35036f2630169ba7d66054881978d1eebc0224eda99"
total_cost
0.001602
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
234
0.00%
Dialogue to Total Word Ratio
Ratio: 41.10%, Deviation: 31.10%
neededClean
false
wordsTotal
236
wordsDialogue
97
0.0001%