NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5BA19JZ0MB7FZPY4W533H
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
46.3s
Cost:
$0.029645
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
98.86%
Dialogue to Total Word Ratio
(details)
99.4313%
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
Molly spread the blueprint across the kitchen table, which was actually a crayon-covered paper placemat stolen from a family restaurant. The target was Mrs. Henderson's backyard, site of little Timmy Henderson's seventh birthday party. Intelligence suggested upwards of twenty wrapped presents piled near the trampoline. Bill squinted through his reading glasses. He was forty-eight, semi-retired, and deeply uncomfortable. "This is a new low, Molly," Bill said. "Oh, please," Molly replied. "We stole garden gnomes last week." Bill tapped the map where Molly had drawn a skull over the bounce house. The plan involved infiltration via the side gate, distraction via clown costume, and exfiltration with a wagon. Molly had already acquired a tactical wagon, bright red with squeaky wheels. She called it the getaway carriage. Bill called it evidence. The backyard perimeter was guarded by parents armed with juice boxes and passive aggressive commentary. The presents themselves were guarded by Timmy, who according to surveillance was prone to tantrums of nuclear proportion. "We need to think about the optics," Bill whispered. "Children crying." "Children always cry," Molly said. "That's their hobby." Molly's plan was simple. Bill would dress as the entertainer, perform balloon animals until the adults were sufficiently bored, then Molly would swoop in dressed as a mom, which mostly meant sensible shoes and a look of quiet desperation. She had practiced the mom nod in the mirror. Bill shook his head. His clown costume smelled of popcorn and regret. The wig itched. He had tried to make a poodle earlier and accidentally made something that looked like a diseased intestine. "What if we get caught?" Bill asked. "We can't outrun children." "We don't need to outrun them," Molly grinned. "We just need to outrun their parents." She pointed to the exit strategy. Once the presents were secured, they would escape through the neighbor's yard, where old Mr. Jenkins left his sprinkler on automatic. It was the perfect cover. No one would chase them while wet. Bill looked at the pile of presents on the reconnaissance photo. There was a Lego set, definitely. Maybe a bike. "Okay, one condition," Bill said finally. "We leave the birthday cake." Molly considered this, pretended to weigh moral consequences, then nodded solemnly. The cake was collateral the universe would not forgive. Outside, a minivan honked. The party had started. Molly checked the wagon's squeaky wheels and winked, already picturing riches beyond toddlers' wildest dreams. "Listen, if we pull this off, we split sixty forty," Molly protested loudly while Bill remained firm. "Sixty forty? I brought the wagon, the plan, and the mom disguise!" "The disguise is just sunglasses and judgment," "Exactly, that's method acting," "Fine, fifty fifty, but I'm keeping the Lego set if there's one." "Deal, but you have to actually wear the clown nose this time." "I will if you promise not to steal the cake by accident again like last year." "That was entrapment, the cake called to me." "Let's go steal some joy before the piƱata breaks." "Ready?"
created_at
"2026-07-25T17:32:12.72Z"
7/25/2026, 5:32:12 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
40653
moderation_latency
(null)
generation_time
46222
tokens_prompt
75
tokens_completion
794
native_tokens_prompt
225
native_tokens_completion
6909
native_tokens_completion_images
0
native_tokens_reasoning
6229
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
0.0296445
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f31d5d8e8055875d43c6"
is_byok
false
latency
1008
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-1785000732-HEMWMF9WKzdskzpCydyt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000732-Ik9OAu1NHdiIp1mPx7rr"
upstream_id
"resp_6a64f31d5d8e8055875d43c6"
total_cost
0.0296445
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
499
98.86%
Dialogue to Total Word Ratio
Ratio: 30.48%, Deviation: 0.48%
neededClean
false
wordsTotal
502
wordsDialogue
153
99.4313%