NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7WWHKQAXW944GCJH7THES
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
24.6s
Cost:
$0.018433
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.76%
Dialogue to Total Word Ratio
(details)
99.8806%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
The van smelled like old fries and regret, which was standard for their operation. Molly spread the blueprints of the suburban house across the dashboard while Bill ate a stolen granola bar meant for a kindergartner. Outside the community center, balloons bobbed against the windows like inflated warnings. A banner reading Happy Birthday Leo sagged heroically. "We are not robbing a six-year-old's birthday party, Bill." Bill looked wounded, which was his default expression when caught being unethical. "Technically we're robbing the parents who bought the presents, which is morally different." He unfurled a crumpled invitation he had clearly taken from a trash can. It was glittery and sticky. "There are juice boxes in there, Molly. Juice boxes and tiny hot dogs. It's a gold mine." Molly stared at him. She had worked with Bill through museum jobs, bank jobs, and one disastrous zoo job involving a peacock. This was a new low, even considering the peacock incident. "And twenty screaming children, a clown, and a mother who runs a CrossFit gym." Bill, however, was already in motion, pulling two sequined vests from a duffel bag that also contained rope, lockpicks, and what appeared to be Capri-Suns. "That's why we need disguises. I'm thinking magician's assistant and slightly taller magician's assistant." She held up a vest. It jingled. "Your last disguise was a fake moustache that fell into the soup. We got banned from Olive Garden." The memory still haunted them. The manager had been very clear about unlimited breadsticks not including unlimited disguises. "This time is different. I've rented an actual bounce house to smuggle the loot out." Molly pinched the bridge of her nose. The parking lot was filling with minivans. Each one delivered another small screaming accomplice to the party. "You want to put stolen Lego sets into a bounce house full of children?" He said it like it was Ocean's Eleven. Molly considered pushing him out of the van, but he was holding the only copy of the exit plan, which was drawn in crayon. "No, we wait until naptime. Or cake time. Kids are useless during cake time." Inside, someone started playing musical chairs badly. A child shrieked with victory. Bill cracked his knuckles dramatically and immediately hurt his hand. "Fine. But if I have to sing Happy Birthday, I'm keeping the goodie bags." "Deal. You handle singing, I handle stealing." "Okay." The plan was terrible. It relied on elastic walls, sugar crashes, and Bill not getting distracted by frosting. Yet somehow, it was also exactly the kind of dumb plan that had always worked for them. Molly sighed, zipped up the ridiculous vest, and checked that the back door was still propped open with a tricycle. The pile of wrapped presents glowed under the buffet table like a small, poorly guarded treasure chest. Outside, the clown car honked. Molly looked at Bill, at the bounce house, at destiny, and regretted every life choice that led here. Still, the Lego sets were limited edition. Very limited.
created_at
"2026-07-25T18:16:45.883Z"
7/25/2026, 6:16:45 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21686
moderation_latency
(null)
generation_time
24454
tokens_prompt
75
tokens_completion
755
native_tokens_prompt
225
native_tokens_completion
4271
native_tokens_completion_images
0
native_tokens_reasoning
3597
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"auto"
usage
0.018433
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64fd8e4e18144bc5f64715"
is_byok
false
latency
280
model_permaslug
"meta/muse-spark-1.1-20260709"
provider_name
"Meta"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785003405-ZwYKctgST8ye8BwzFkcg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003405-rPOWDOnQ7IDO0yWHkNJk"
upstream_id
"resp_6a64fd8e4e18144bc5f64715"
total_cost
0.018433
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
99.76%
Dialogue to Total Word Ratio
Ratio: 30.22%, Deviation: 0.22%
neededClean
false
wordsTotal
503
wordsDialogue
152
99.8806%