NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09DEZ2QW5JR0DN7Q04S76M
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
1.9s
Cost:
$0.001363
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
40.6364%
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
“Ready, Bill?” Molly whispered, peering through the hedge at the balloon-bright house. “Ready as a locksmith at a skeleton-key convention,” Bill whispered back, tugging his black gloves straight. “You’re sure this is the right party?” “Of course. Blue streamers, clown on the lawn, suspiciously many tiny chairs. It screams children.” Bill frowned. “It also screams cupcakes.” “Focus. We are here for the presents.” “Right. The presents,” he said, checking his bag. “I’ve brought the flashlight, the crowbar, and a small emergency hat.” “A hat?” “For blending in. If someone asks, I’m with the entertainment.” Molly snorted. “You? Entertaining?” “I contain multitudes.” Inside, a squeal rose, followed by the shriek of a balloon animal popping. Molly winced. “That sounded expensive.” Bill leaned closer. “Question: are we stealing from the gift table, or from the kids after they open them?” “Bill!” “What? Efficiency matters.” “No. We take the unopened presents, the sensible way.” “Shame. I had a whole strategy involving gift wrap and tears.” Molly cracked her knuckles. “In, grab, vanish.” “And if we’re caught?” “Smile politely.” Bill nodded. “You’re the brains.” “And you’re the one carrying the emergency hat.”
created_at
"2026-03-18T10:56:11.759Z"
3/18/2026, 10:56:11 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
349
moderation_latency
(null)
generation_time
1800
tokens_prompt
77
tokens_completion
381
native_tokens_prompt
66
native_tokens_completion
292
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
0.0013635
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_067d2fab52cc62b70169ba84cbcfcc8195bae658d7a56f499f"
is_byok
false
latency
172
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-1773831371-nHtnUZhgvehf0CHkSyzu"
upstream_id
"resp_067d2fab52cc62b70169ba84cbcfcc8195bae658d7a56f499f"
total_cost
0.0013635
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
0.00%
Dialogue to Total Word Ratio
Ratio: 72.63%, Deviation: 22.63%
neededClean
false
wordsTotal
190
wordsDialogue
138
40.6364%