NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5GJ7X5QKWVSKD7KCYFY34
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 59s
Cost:
$0.034910
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 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
Molly spread the stolen party map across the van dashboard while Bill chewed cold fries thoughtfully. "Bill, we are absolutely not wearing clown suits again." "Last time worked perfectly until you laughed at the magician." Bill adjusted his fake mustache which kept curling upward like a guilty caterpillar. "I did not laugh, I snorted juice through my nose in surprise." "Six kids cried, one pinata filed a complaint, and we got nothing." Rain tapped the windshield as children screamed happily inside the bright community center nearby. "This time we go as tired parents with coffee and regret." "Perfect cover, nobody questions tired parents at a kids party." Molly tossed him a stained trench coat and pointed at the colorful balloons bobbing outside. "Exactly, we walk in during cake, grab presents during singing." "What about the bouncy castle guard, that kid is huge." A banner read Happy Birthday Lucy in glittery letters that sparkled even through gloomy afternoon light. "Timmy is seven, Bill, bribe him with extra cake." "Fine, but the gift table is right next to the moms." Bill sighed loudly and stuffed blueprints for the community hall into his soggy back pocket. "You distract with small talk about nap schedules and taxes." "I do not know anything about naps or taxes, Molly." Molly checked her watch, counted minivans in the parking lot, then smiled with professional criminal pride. "Just nod sadly and say mine never sleeps, works every time." "Okay, then you stuff presents into the diaper bag." Outside a clown bicycled past slowly, ringing a bell with deeply suspicious cheerfulness. "Biggest diaper bag ever, fits a tricycle if we try." "What if they count presents before we leave, huh?" Bill ducked instinctively, knocking over cold coffee and scattering crumpled napkins across the van floor. "Kids never count presents, they just scream for more." Molly grabbed a notebook filled with doodles of exits, cake tables, and excellent escape routes. "True, last birthday I saw chaos, frosting, total anarchy." The air smelled like old fries, wet socks, and faintly vanilla frosting from next door. "So Saturday at two, bring coffee, act exhausted, steal loot." Bill wiped mustard from his chin and tried to look like a respectable exhausted father. "Deal, but if clowns appear, I am running immediately." Molly snorted, tossed him dark sunglasses, then pointed toward the side entrance near dumpsters. "Agreed, no clowns, no magic, just presents and escape." Children chanted happily for cake while harried parents herded toddlers wearing pointy party hats. "Should we wrap an empty box to blend in nicely?" Bill cracked his knuckles nervously, Molly grinned widely, both imagining piles of wrapped toys. "Brilliant, put rocks inside, label it love from Uncle Bill." Thunder rumbled faintly as they bumped fists, ready for the silliest heist ever attempted. "They will hate Uncle Bill, perfect alibi for us." Molly started the van engine softly while Bill practiced his tired dad sigh perfectly. "Exactly, now stop practicing your sneaky face, please." "This is normal face." Showtime approached.
created_at
"2026-09-03T08:17:37.043Z"
9/3/2026, 8:17:37 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4006
moderation_latency
(null)
generation_time
119208
tokens_prompt
75
tokens_completion
809
native_tokens_prompt
68
native_tokens_completion
8194
native_tokens_completion_images
0
native_tokens_reasoning
7482
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
0.0349095
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423457-WnixMLX6CgU5Lf1EJR6x"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423457-nMgyaf8VJSNn8ETa58df"
upstream_id
"resp_6a992d210ce2c11836c14b1a"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992d210ce2c11836c14b1a"
is_byok
false
latency
523
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.0349095
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%