NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09KGKCF79T7JJHDX6QMJF8
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.1s
Cost:
$0.001908
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
10.0948%
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 leaned over the moonlit fence and whispered, “Bill, tell me you brought the snacks.” Bill adjusted his black cap. “I brought the gloves, the crowbar, and an emotional support biscuit. Priorities.” “Good. Because nothing says professional thief like oat crumbs.” “Focus,” Bill said. “The party starts at three. Children. Clowns. A bouncy castle.” “Terrifying,” Molly said. “Especially the clowns.” “We slip in, mingle, and vanish with the presents.” Molly squinted at the house. “How many presents?” “Enough to make one child weep into a paper crown.” “Cruel, Bill.” “Efficient.” A burst of laughter floated from the yard, followed by a shriek of delight. Molly grinned. “Hear that? Untapped chaos.” Bill nodded. “The gift table is by the shed. I counted one golden retriever, two parents, and a suspicious man in a dinosaur costume.” “Ah,” Molly said. “The usual security detail.” “We cut through the bunting, lift the sacks, and exit through the side gate.” “And if we’re caught?” Bill raised an eyebrow. “We pretend we’re the entertainment.” Molly gasped. “Bill, you’re a genius.” “I know.” She offered her gloved hand. “For the children’s presents.” He shook it. “For the children’s presents.” “And,” Molly added, “for the biscuits.” “For the biscuits,” Bill agreed, and together they crept toward the party, smiling like villains and stepping carefully around the lawn gnomes.
created_at
"2026-03-18T10:59:30.041Z"
3/18/2026, 10:59:30 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2560
moderation_latency
(null)
generation_time
2891
tokens_prompt
77
tokens_completion
541
native_tokens_prompt
66
native_tokens_completion
413
native_tokens_completion_images
0
native_tokens_reasoning
75
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
0.001908
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_092900f955ecf3b10169ba85921d5481949650835e451a4eca"
is_byok
false
latency
226
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-1773831570-KvFUSw8DwXkk6a3cTrH2"
upstream_id
"resp_092900f955ecf3b10169ba85921d5481949650835e451a4eca"
total_cost
0.001908
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
220
0.00%
Dialogue to Total Word Ratio
Ratio: 65.00%, Deviation: 25.00%
neededClean
false
wordsTotal
220
wordsDialogue
143
10.0948%