NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07X357ZQZ4VNX2PKN33R4B
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.3s
Cost:
$0.001548
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
84.0244%
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
“Molly, tell me again why we’re stealing from a room full of sugar-fueled six-year-olds,” Bill whispered. “Because, Bill, unlike your last job, the loot won’t bite back.” “My last job was a bird sanctuary.” “And the geese won.” Bill peeked through the hedge. “That’s a lot of balloons.” “That’s a lot of gifts,” Molly said. “Bicycle. Train set. Seven dolls. Possibly a small drum kit. Christmas has been kidnapped by a clown.” “Why are there clowns at a birthday party?” “Why are there always clowns? Focus.” “I am focused. I’m just saying, if we get caught, I’m blaming your ‘simple’ plan.” “My plan is elegant. We blend in.” “With what? Our faces?” “We put on the spare party hats.” Bill stared. “These are tiny hats.” “They’re festive tiny hats.” “Mine has a dinosaur on it.” “Perfect. Dinosaurs inspire trust.” A child shrieked inside. Bill flinched. “That sounded expensive.” “Probably the piñata,” Molly said. “Listen carefully. We enter with the cake, distract with applause, and while they’re singing, we walk out with the presents.” “You’re assuming they’ll let us carry the cake.” “They won’t.” “Then how do we get in?” Molly grinned. “Bill, for once, we arrive as the entertainment.” Bill sighed. “I hate that you’re right.” “Correction,” Molly said. “You hate that I’m brilliant.”
created_at
"2026-03-18T10:29:46.805Z"
3/18/2026, 10:29:46 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
411
moderation_latency
(null)
generation_time
1759
tokens_prompt
77
tokens_completion
416
native_tokens_prompt
66
native_tokens_completion
333
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
0.001548
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_073fadb43248bc9d0169ba7e9adf688190ab7c81087e4a735d"
is_byok
false
latency
173
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-1773829786-hH6jjAmHI0DK6Y2Gfb7L"
upstream_id
"resp_073fadb43248bc9d0169ba7e9adf688190ab7c81087e4a735d"
total_cost
0.001548
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
214
99.95%
Dialogue to Total Word Ratio
Ratio: 88.48%, Deviation: 1.52%
neededClean
false
wordsTotal
217
wordsDialogue
192
84.0244%