NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM091NAWWKD5RV62FGTNJ57E
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.0s
Cost:
$0.001391
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3577%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 peered through the bakery window at the inflatable castle glowing in the park. “There,” she said, tapping the glass. “Children’s party. Easy pickings.” Bill adjusted his gloves. “You really think toddlers are going to notice a couple of professionals?” “They’ll notice when their presents vanish,” Molly said. “That’s why we’re not professionals. We’re artists.” Bill snorted. “Artists don’t usually wear ski masks shaped like dinosaurs.” “Minimalism is back,” Molly said. “We blend in.” “With who? The other criminals at the preschool?” Molly folded a napkin into a perfect map. “Listen. Cake table on the left, balloon arch in the center, gift mountain by the pirate ship. We slip in during the clown’s magic act.” Bill frowned. “What if the clown spots us?” “Then we distract him.” “With what?” “Your face,” she said. He laughed despite himself. “You’re charming when you’re terrible.” “I know. Now, do you have the getaway scooter?” Bill patted a tiny folding scooter under his coat. “Suspiciously yes.” “Good,” Molly said, sliding a spoon into her sleeve. “We take the presents, vanish into the alley, and by lunch these children will be crying into juice boxes.” Bill grinned. “And us?” “We,” said Molly, “will be rich, infamous, and possibly covered in frosting.”
created_at
"2026-03-18T10:49:45.063Z"
3/18/2026, 10:49:45 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
393
moderation_latency
(null)
generation_time
1878
tokens_prompt
77
tokens_completion
387
native_tokens_prompt
66
native_tokens_completion
298
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
0.0013905
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0780f51d4b8a7fd50169ba8349208481969ab4d72dfde2f8bd"
is_byok
false
latency
184
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-1773830985-ylXw6CQQ7cpWpWECQHBZ"
upstream_id
"resp_0780f51d4b8a7fd50169ba8349208481969ab4d72dfde2f8bd"
total_cost
0.0013905
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 67.96%, Deviation: 17.96%
neededClean
false
wordsTotal
206
wordsDialogue
140
49.3577%