NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M755JCK0XEKBBBX1BFNXYFNN
Run Details
Model:
Muse Ember (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
11.1s
Cost:
$0.003722
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 spread a napkin map across the sticky motel table while Bill balanced three juice boxes and a stolen cupcake on his nervous knee beside a glittery party invitation tonight. "Listen, Bill, the Johnson twins turn seven tomorrow, and every rich kid in town is bringing presents stacked taller than their pony. We sneak in during musical statues. That gives us perfect cover. Absolutely perfect." "Molly, I love your ambition, but last time we robbed a lemonade stand, the toddler union blacklisted us. Children are ruthless, tiny, and permanently sticky. They also share terrifying intelligence networks. And absolutely terrible cake." Bill chewed his pen until it squeaked, then pointed at the napkin where Molly had drawn the backyard, the bouncy castle, and a suspiciously large cake with innocent crayon arrows. "Okay, plan A: I dress as a clown, you dress as a normal parent. Nobody questions a clown, especially one carrying balloon animals and minor emotional damage. It is basically an invisibility cloak. Very practical." "Plan B sounds better because I already own a clown nose from our failed circus job. Besides, you have a clown phobia and faint whenever horns honk nearby. That creates unnecessary screaming and chaos unfortunately." Outside, rain tapped the motel window while a distant ice cream truck played a warped jingle that sounded exactly like a tiny criminal confession through the damp night air ominously. "Fine, you wear the clown suit, and I will pose as an exhausted mother carrying a fake baby named Gerald. Parents never suspect other parents, Bill. Gerald is just a water balloon with a bonnet." "Perfect, except Gerald will cry whenever sprinklers activate. That happened at the aquarium and security chased us out using one of those little fishing nets. I still have seaweed in my shoe. Since that Tuesday." Molly flipped the invitation over and read the party schedule aloud, tapping each activity with a chewed red pencil while Bill nodded far too enthusiastically for sweet, sweet cake already. "At three, pin the tail. At four, pinata. At five, presents. We strike during pinata because candy rain distracts every adult and most of the children too. We grab everything and bolt toward the trampoline." "Molly, the trampoline launches us into the neighbor's pool. Last summer we landed there and the neighbor's parrot learned our names and now shouts them constantly. It knows our entire criminal history. Probably judges us." Bill rolled up the napkin map, tucked it inside his jacket, and tried to look casual while Molly sharpened a plastic spoon like a weapon for the eventual cake battle. "Then we escape through the garden gate, hijack a passing ice cream truck, and hide the presents under a giant inflatable flamingo until the heat dies down. That flamingo has already survived two hurricanes. Somehow." "Brilliant, Molly, absolutely brilliant. After this, we retire, buy a beach house, and never return to children's parties unless absolutely desperate for cake. Or maybe one tiny present for Gerald. He deserves a little toy."
created_at
"2026-11-11T11:23:25.669Z"
11/11/2026, 11:23:25 AM
model
"meta/muse-ember-20261109"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2620
moderation_latency
(null)
generation_time
11029
tokens_prompt
75
tokens_completion
988
native_tokens_prompt
69
native_tokens_completion
7431
native_tokens_completion_images
0
native_tokens_reasoning
6602
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
"default"
usage
0.0037224
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794396205-tPrHU9owGZYE95oEMHMA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794396205-oXxuMFjQIiH40XSwvPuG"
upstream_id
"resp_6af4502f9f6e9f01b2d04e96"
provider_responses
0
endpoint_id
"ea8469c2-ddf8-4985-8cf2-f5dc7e63e14c"
id
"resp_6af4502f9f6e9f01b2d04e96"
is_byok
false
latency
1468
model_permaslug
"meta/muse-ember-20261109"
provider_name
"Meta"
status
200
total_cost
0.0037224
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 70.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
350
100.0000%