NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5G24YKADANKDZVZ4755AG
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
27.7s
Cost:
$0.019387
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
98.79%
Dialogue to Total Word Ratio
(details)
99.3878%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 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
The getaway van smelled faintly of old pizza and desperation. Molly spread blueprints across the dashboard while Bill tried to untangle a giant Happy Birthday banner from the steering wheel. Outside the suburban house, a clown was making balloon animals that looked faintly terrified. "Listen, Bill, we have robbed banks, museums, and one very aggressive casino in Reno." Bill squinted at the blueprints, which turned out to be a crumpled Chuck E. Cheese placemat. "This says we enter through the bouncy castle, right?" Molly snapped the placemat flat with the precision of a surgeon. "Exactly. The kids will be distracted by the magic show at three. That is our window." Bill frowned at a hand-drawn X marked presents piled higher than a small adult. Bill adjusted his ill-fitting clown nose which honked mournfully. "I still do not understand why we are stealing from a six-year-old, Molly. Seems low, even for us." Molly stared at him like he had suggested robbing a lemonade stand with mean girl scouts. "It is not a six-year-old, it is Brayden's mom. She invited every rich kid in Westchester. Those presents are solid gold. Plated, but still." Outside, a line of tiny guests arrived clutching boxes wrapped in glitter that cost more than their van. "What if someone recognizes us? We are on at least two watchlists." Molly pulled two oversized birthday hats from a duffel bag that also contained lockpicks and juice boxes. She tossed one to Bill who caught it like it might explode. "Nobody will recognize two totally normal parents. Just act like you love Paw Patrol and hate taxes." "We walk in, grab the mountain, and leave before the cake." Bill put on the hat. It was too small and made him look like an anxious conehead. The clown outside popped a balloon and three children screamed with delight. "Do we have an exit strategy?" "Yes. We yell 'diaper blowout' and run." Bill nodded slowly, finally understanding the true criminal genius before him. He straightened his clown nose for courage. "You are terrifying, Molly. Let us go steal some Legos." They opened the van doors and marched toward certain doom disguised as a bounce house. Molly checked her watch shaped like a unicorn. The driveway was lined with tiny shoes and one very judgmental inflatable dinosaur guarding the presents. "That dinosaur is security, so smile at it. If the clown sees us taking the pile, you distract him with balloon animal requests." "What kind of balloon animal should I request? Something intimidating?" "A reasonable 401k and emotional stability, but settle for a poodle." "Got it. Poodle equals panic, poodle equals panic." "If we get caught, we tell them we thought it was a take-one-give-one situation." "Brilliant. Nobody suspects charity. Now move, before someone cuts the cake without us." "One last thing, what if Brayden cries when his mountain vanishes?" "We leave a business card. Future clients love trauma." "Let us go rob childhood itself." They walked faster. And they did.
created_at
"2026-07-25T17:34:48.486Z"
7/25/2026, 5:34:48 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
24719
moderation_latency
(null)
generation_time
27589
tokens_prompt
75
tokens_completion
772
native_tokens_prompt
225
native_tokens_completion
4512
native_tokens_completion_images
0
native_tokens_reasoning
3829
native_tokens_cached
64
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
0.01938685
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f3b875128a15a22442c2"
is_byok
false
latency
395
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-1785000888-jHayZFiBrTU6vu5qYHnw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000888-d0fMKcar38ePRwIajAnk"
upstream_id
"resp_6a64f3b875128a15a22442c2"
total_cost
0.01938685
cache_discount
0.0000704
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
498
98.79%
Dialogue to Total Word Ratio
Ratio: 50.49%, Deviation: 0.49%
neededClean
false
wordsTotal
507
wordsDialogue
256
99.3878%