NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A13MJPP1TEYXJ6B7J9J88
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.3s
Cost:
$0.003334
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.6886%
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 flattened the party invitation against the rain-slick alley wall and grinned. Through the kindergarten gym windows, streamers bobbed like surrender flags, and a mountain of wrapped presents sat beneath a cardboard castle. Bill, wearing a borrowed balloon hat, adjusted his gloves and tried not to look emotional. “Those boxes are begging for liberation,” he whispered. Molly peered at the timetable on her watch. “Cupcake break in seven minutes. That’s our window.” Bill nodded toward the side door, where a paper sign read, PLEASE WASH HANDS BEFORE ENTERING. “Nice to know the defense budget is low,” he said. Molly handed him the tiny trolley they’d stolen from a supermarket display. “We roll in as the clown’s equipment team, grab the gifts, and vanish before anyone notices the missing dinosaur-themed bag.” Bill blinked. “And if they do?” Molly shrugged. “We blame the magician. Everyone blames the magician.” Inside, a speaker began playing “Happy Birthday” with enough enthusiasm to frighten a horse. Bill swallowed, squared his shoulders, and smiled like a man about to commit a highly organized felony. Molly touched the door handle. Somewhere within, a child laughed, and the presents waited, glittering with terrible innocence.
created_at
"2026-03-18T11:06:55.519Z"
3/18/2026, 11:06:55 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7787
moderation_latency
(null)
generation_time
8124
tokens_prompt
77
tokens_completion
564
native_tokens_prompt
66
native_tokens_completion
730
native_tokens_completion_images
0
native_tokens_reasoning
466
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
0.0033345
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_04f2eb339c36fc930169ba874f91e8819698b87ca314cc3f18"
is_byok
false
latency
170
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-1773832015-d0zpfrTJxVdBw7P8Gtry"
upstream_id
"resp_04f2eb339c36fc930169ba874f91e8819698b87ca314cc3f18"
total_cost
0.0033345
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
0.00%
Dialogue to Total Word Ratio
Ratio: 28.93%, Deviation: 18.93%
neededClean
false
wordsTotal
197
wordsDialogue
57
49.6886%