NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBV9BKHMGDHXERQVC12QXZ
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
25.0s
Cost:
$0.089892
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.36%
Dialogue to Total Word Ratio
(details)
99.6821%
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
The warehouse smelled of glitter, stale popcorn, and questionable decisions while rain hammered the crooked roof above their stolen folding table on Tuesday. Bill tapped the map and said, "Molly, tell me again why stealing presents from eight-year-olds counts as a brilliant criminal master plan today." Molly examined the map, which depicted a suburban garden, several ferocious stick figures, and a treasure table guarded by one extremely suspicious-looking cupcake. She smiled and replied, "Because adults guard banks, Bill, but children guard cake, and cake guards collapse instantly when balloons appear." Bill nodded slowly, although his left eye twitched whenever he imagined performing before children who could smell fear, desperation, and cheap face paint. He asked, "So we dress as clowns, juggle suspiciously, grab every wrapped box, and sprint past the bouncy castle?" Molly stood, produced two rainbow wigs from a duffel bag, and tossed the itchiest one directly onto his already regretting head with triumph. She explained, "Exactly, except you juggle rubber chickens while I sweet-talk grandma and locate the mountainous gift table." Bill adjusted the wig, sneezed glitter across the blueprints, and contemplated a quieter career involving libraries, fake mustaches, or moderately honest plumbing work. He complained, "My clown shoes squeak louder than police sirens, Molly, and my nose keeps falling into soup." Molly rummaged through their costume trunk and discovered tap shoes, three custard pies, a kazoo, and handcuffs apparently borrowed from a magician. She declared, "Then wear tap shoes quietly, genius, and blame musical entertainment whenever anyone questions your ridiculous honking footsteps." Outside, thunder applauded while Bill practiced smiling beneath greasepaint until his reflection looked like a haunted pancake attending its own surprise party alone. He whispered, "What happens when Timmy demands balloon animals and exposes us as frauds with absolutely no skills?" Molly inflated a balloon using sheer confidence, twisted it into something resembling spaghetti, and presented the wobbling creation with theatrical pride and flourish. She instructed, "You inflate balloons, twist randomly, shout dinosaur, and pray childhood imagination performs the heavy lifting." Bill studied their escape drawing, featuring arrows, hedges, a getaway tricycle, and warnings written in increasingly panicked capital letters underlined three times each. He demanded, "And escape route, fearless leader, preferably one avoiding sprinklers, ponies, parents, and that terrifying piƱata bat." Molly rose, crossed the warehouse in three silent strides, opened the rusty side door, and revealed a moonlit alley ending beside a tall, forgiving hedge beyond the unsuspecting family's garden fence. She pointed outside and cried, "Through the hedge!" Bill laughed, folded the crayon map into his oversized pocket, and followed her into the damp night, both thieves rehearsing cheerful honks, innocent expressions, and increasingly implausible explanations for carrying forty presents through suburbia before breakfast while somewhere across town, an unsuspecting birthday cake cooled beside stacked gifts, colorful ribbons, sleepy balloons, and one small guard dog whose heroic barking would shortly transform their flawless plan into glorious, unforgettable chaos for everyone involved despite their confidence, optimism, and truly spectacular lack of common sense.
created_at
"2026-10-13T10:10:06.333Z"
10/13/2026, 10:10:06 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1943
moderation_latency
(null)
generation_time
24967
tokens_prompt
75
tokens_completion
1006
native_tokens_prompt
68
native_tokens_completion
4481
native_tokens_completion_images
0
native_tokens_reasoning
3667
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
0.089892
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886206-OB5VrL8pyaLpSxxNNZ2t"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886206-r3dsjLwfdvML45IKwcjQ"
upstream_id
"resp_6ace037ec786ec201d99467d"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace037ec786ec201d99467d"
is_byok
false
latency
502
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.089892
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
99.36%
Dialogue to Total Word Ratio
Ratio: 30.36%, Deviation: 0.36%
neededClean
false
wordsTotal
504
wordsDialogue
153
99.6821%