NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5TJNHWM1JDPTCSGS4E39B
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 39s
Cost:
$0.035772
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 crouched behind the blue minivan across from Sunny Meadows Community Hall watching parents carry bright wrapped boxes inside while balloons bobbed wildly in wind. "That is a fortress of juice boxes and frosting, Moll, but I count at least forty presents stacked by the clown table right now today." Bill nodded solemnly while adjusting a lopsided clown nose that squeaked every time he breathed and made his fake caterer vest look even less convincing. "Relax, genius, we walk in with the extra cake, smile at the tired mom brigade, then load every truck shaped gift during musical chairs chaos." A small child in a pirate costume sprinted past them screaming for cupcake justice while a tired magician dropped his rabbit cage onto the sidewalk. "Musical chairs chaos is not a real cover, Molly, those kids are vicious and that birthday boy looks like he bites strangers for fun daily." Molly pulled out a crumpled floor plan drawn in crayon on a napkin showing the gift table beside the bouncy castle and the cake exit. "Bouncy castle is our Trojan horse, Bill, we deflate one side slowly, create a glorious distraction, then wheel presents out in the stroller van today." Bill stared at their getaway car covered in baby stickers with a car seat stuffed full of empty duffel bags and crushed goldfish crackers again. "I still think stealing from six year olds is low, even for us, can we at least leave the sad sock gift from grandma behind?" Molly snorted and tossed him a party hat with elastic that snapped painfully against his ear while parents inside began singing off key happy birthday. "Morals later, loot now, birthday boy gets like triple duplicates anyway, we are basically providing present recycling for over gifted suburban children everywhere today folks." Through the window they watched the clown twist a balloon giraffe that immediately popped and sent five toddlers into dramatic wailing despair at once loudly. "Perfect, crying toddlers mean distracted adults, I will pose as Giggles the backup clown while you crawl under the gift table for extraction quietly now." Molly grinned wickedly and produced two walkie talkies shaped like dinosaurs that only squawked static and random roaring noises when buttons were pressed hard today. "Code names are Princess Sparkle and Sir Poopsalot, if anyone asks your age, cry immediately, kids never question another kid having a beard seriously dude." Bill sighed deeply and pulled the rainbow wig over his balding head as sprinkles from a nearby donut truck drifted onto his fake vest slowly. "Fine, but if I get tackled by the birthday boy again like last year, you owe me extra juice pouches and full dental coverage forever." Molly linked arms with him and marched toward the blaring party music ready to steal joy, frosting, and every single poorly wrapped present inside today. "Remember, smiles wide, pockets empty at start, exit with cake in hand, nobody suspects the couple carrying triplets and twelve leaking goodie bags ever buddy."
created_at
"2026-09-03T08:23:05.143Z"
9/3/2026, 8:23:05 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4375
moderation_latency
(null)
generation_time
99348
tokens_prompt
75
tokens_completion
775
native_tokens_prompt
68
native_tokens_completion
8397
native_tokens_completion_images
0
native_tokens_reasoning
7751
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
0.03577225
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423785-exBXvIr91wzcSrvRNtb0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423785-hpORyTUKH0zi7OE7w31K"
upstream_id
"resp_6a992e6afd089fe927494f56"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992e6afd089fe927494f56"
is_byok
false
latency
1081
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.03577225
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%