NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5P17A088S1PF7BGWNHMED
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
40.8s
Cost:
$0.030154
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9677%
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 van smelled faintly of old french fries and desperation. Molly had parked two houses down from the bouncy castle, binoculars pressed to her eyes while Bill tried to look inconspicuous in a stolen clown wig. The street was quiet except for the distant thump of children's music and the hiss of a grill where a dad was burning burgers with intense concentration. "Okay, so walk me through the plan again," Bill said. "We are robbing a six-year-old?" "We are liberating presents from a six-year-old," Molly corrected. "There's a difference." "Morally or legally?" "That kid is getting twenty gifts. That's better than the jewelry store." Bill adjusted his squeaky red nose. "The jewelry store had cameras. This has moms. Moms are worse." Molly lowered the binoculars. Across the street, a banner read HAPPY BIRTHDAY JAYDEN! and a clown was twisting balloons into what looked like tortured poodles. A table near the back was piled high with brightly wrapped boxes. Molly's eyes gleamed. She had cased grocery stores, gas stations, even a dentist's office, but nothing had ever looked so poorly guarded and so beautifully wrapped. "Look at that table," Molly whispered. "That is a mountain of potential. Legos, video games, cash in cards." "So we just walk in?" Bill asked. "No, we create a distraction. You do your clown thing." "I don't have a clown thing." "You practiced the balloon animals for three days." "I can only make a snake. Every animal ends up a snake." Molly sighed and pulled a duffel bag onto her lap. "Fine. Plan B. I go in as the entertainer. You wait by the gate with the bag. When I signal, you grab the presents." "What's the signal?" "I'll yell surprise!" "At a surprise party? That's confusing." "It's a birthday party, Bill. Everything is a surprise at six." Bill stared at the yard. A dozen screaming children chased each other with juice boxes. A harried father was trying to keep the cake from collapsing in the heat. "I still feel weird stealing from kids," Bill muttered. "Can't we hit a bank?" "Banks have vaults. Jayden has wrapping paper. Which can you open with scissors?" "The presents, obviously." "Exactly. Low security, high reward. Nobody expects present thieves." Molly checked her watch. "The magic show starts in five minutes. That's our window. The parents will be distracted. We slip in, we slip out." "And if we get caught?" Bill asked. "We say we're performance artists." "And if they call the cops?" "We run. Very fast artists." A warm wind carried the smell of frosting and sunscreen. Somewhere, a child screamed with delight as the bouncy castle deflated slightly under the weight of too many jumpers. Molly opened the van door. The sound of children shrieking Happy Birthday off-key rolled down the street. "Ready?" she asked, pulling on a bright pink magician's cape. Bill took a deep breath, his wig tilting sideways. "For the record, the snake balloon is charming." "It is," Molly said. "Now let's steal some childhood innocence."
created_at
"2026-09-03T08:20:36.21Z"
9/3/2026, 8:20:36 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2970
moderation_latency
(null)
generation_time
40715
tokens_prompt
75
tokens_completion
785
native_tokens_prompt
68
native_tokens_completion
7075
native_tokens_completion_images
0
native_tokens_reasoning
6359
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
0.03015375
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423636-KlfCiijnceYSyfIydKVz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423636-0FyTcmGqPTPKHWTQYOjT"
upstream_id
"resp_6a992dd4610d9b11c85d4e40"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992dd4610d9b11c85d4e40"
is_byok
false
latency
580
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.03015375
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
99.98%
Matches word count
n/a
neededClean
false
words
502
99.95%
Dialogue to Total Word Ratio
Ratio: 49.90%, Deviation: 0.10%
neededClean
false
wordsTotal
507
wordsDialogue
253
99.9677%