NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09M96WYC8KBVXCZJ5F4HM8
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.3s
Cost:
$0.001575
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 crouched behind the bakery dumpster, studying the glittering flyer she’d swiped from a lamppost. “Children’s birthday, Saturday, three until six. Clown. Pony. Gift table.” She grinned. “It’s a treasure map with frosting.” Bill adjusted his stolen bow tie. “You’re calling it a treasure map because you’re nervous.” “I’m calling it a treasure map because treasure maps are classy.” He squinted at the list. “We need a plan.” “We need disguises.” “Why is every plan of yours one wool hat away from stupidity?” Molly opened a satchel. “Because stupidity is cheap and effective. Behold: giant mascot costumes.” Bill stared. “Those are pink rabbits.” “Exactly. Nobody suspects pink rabbits.” “Nobody suspects pink rabbits because nobody wants to think about pink rabbits.” Molly handed him one. “Put it on. We enter as entertainment, drift toward the presents, and exit before the cake.” Bill hesitated. “What if the children ask for a performance?” “We tell them a story about a rabbit who found a mountain of loot and retired very rich.” “That’s not a children’s story.” “It is if we leave out the prison part.” Bill sighed, tugging on the rabbit head. “If this works, I’m never trusting you again.” Molly smiled. “That’s the spirit. Now hop.”
created_at
"2026-03-18T10:59:55.241Z"
3/18/2026, 10:59:55 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
779
moderation_latency
(null)
generation_time
1893
tokens_prompt
77
tokens_completion
374
native_tokens_prompt
66
native_tokens_completion
339
native_tokens_completion_images
0
native_tokens_reasoning
46
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
0.001575
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0b27d66aa6fb2c2b0169ba85ab4fdc8195bed7fe83ebd4f781"
is_byok
false
latency
211
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-1773831595-evedL1y5z3UdYJDZ5lu2"
upstream_id
"resp_0b27d66aa6fb2c2b0169ba85ab4fdc8195bed7fe83ebd4f781"
total_cost
0.001575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
0.00%
Dialogue to Total Word Ratio
Ratio: 75.98%, Deviation: 25.98%
neededClean
false
wordsTotal
204
wordsDialogue
155
49.8722%