NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09Q7FYECR3MQZS5C7ATZJZ
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1.9s
Cost:
$0.001409
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
23.84%
Dialogue to Total Word Ratio
(details)
58.7463%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
“We’re really doing this?” Molly whispered. “Obviously,” Bill whispered back. “It’s a children’s party, not Fort Knox.” “You said that about the bakery.” “I maintain the bakery was guarded by very determined scones.” Molly peered through the hedge. “There are balloons.” “Yes,” Bill said. “A classic distraction. Also, terrifyingly cheerful.” “And clowns?” “One clown,” Bill said. “Which is one too many clowns.” Molly adjusted her gloves. “We are robbing children.” “We are liberating presents from an overorganized gifting economy.” “That sounds worse.” “It sounds professional.” A burst of singing drifted from the garden. Molly winced. “They’re doing ‘Happy Birthday.’” “Perfect cover,” Bill said. “No one hears rustling wrapping paper over a chorus of tiny lungs.” “Tiny lungs?” “Metaphorically,” Bill said. “Focus. You take the left side, I’ll handle the table.” “If there’s a piñata, I’m leaving.” “If there’s a piñata, we’re upgrading the operation.” Molly frowned. “You really think the presents are unattended?” Bill smiled. “Molly, this is a room full of sugar, scissors, and adults pretending to supervise.” “That is disturbingly persuasive.” “Then onward,” Bill said. “Tonight, we become legends.” “Or criminals with sticky fingers.” “Same business card,” said Bill.
created_at
"2026-03-18T11:01:31.788Z"
3/18/2026, 11:01:31 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
430
moderation_latency
(null)
generation_time
1569
tokens_prompt
77
tokens_completion
417
native_tokens_prompt
66
native_tokens_completion
302
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
0.0014085
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_07c79a96f726da4e0169ba860bda9c8196b552f29d8e970669"
is_byok
false
latency
255
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-1773831691-lpLeQklL9eB9UDAXiGbX"
upstream_id
"resp_07c79a96f726da4e0169ba860bda9c8196b552f29d8e970669"
total_cost
0.0014085
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
23.84%
Dialogue to Total Word Ratio
Ratio: 79.06%, Deviation: 10.94%
neededClean
false
wordsTotal
191
wordsDialogue
151
58.7463%