NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TC032MSDXNDXW9AFKWEQY5
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
31.1s
Cost:
$0.108072
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 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 abandoned arcade smelled of burnt popcorn, damp carpet, and spectacularly bad decisions, which made it perfect headquarters for two thieves whose combined luck could curdle milk at fifty paces during winter. Molly studied the hand drawn map while Bill practiced tiptoeing between silent pinball machines wearing rainbow clown shoes. "Bill, we are absolutely not wearing clown shoes for this job, they squeak, they trip, and they make you look emotionally unstable." Bill lifted one foot and produced a honk so mournful that three pigeons outside reconsidered their lives. He pointed toward the party invitation taped above a broken photo booth, where letters announced Timmy Turner's eighth birthday extravaganza, complete with ponies, magicians, expensive presents, and absolutely no adult supervision worth fearing. "The squeaking is the cover, Molly, nobody questions a clown at a birthday party, they just pray he leaves before the sugar crash." Molly rubbed her temples and recalled the disastrous aquarium job, the vengeful octopus, the wet tuxedos, and Bill's heroic attempt to negotiate with security using balloon animals shaped like legal documents nobody respected. She tapped the map twice, directly over the garden gate drawn beside the neighbor's enthusiastic rose bushes. "Last time you went undercover as entertainment, you cried during musical chairs and refused to surrender the final seat to a seven year old." Bill winced, adjusted his red nose, and solemnly raised one hand like a man testifying before congress about events involving cake, treachery, and a child who had trained with tiny assassins during summer camp. Outside, rain polished the windows while thunder applauded sarcastically somewhere beyond the darkened distant rooftops tonight. "That kid had dead eyes and elite footwork, I panicked, besides, this time we grab the presents, swap in decoys, and vanish before cake." Molly leaned closer, suddenly interested despite every sensible instinct screaming for early retirement in a quiet village where nobody owned wrapping paper. Bill unfolded three gift bags patterned with dinosaurs, superheroes, and tax evasion, then demonstrated his decoy technique by producing a brick wrapped so beautifully that Molly nearly applauded. "Decoys weighted with what, exactly, because those children will shake every box like bomb disposal experts hunting for Lego and disappointment?" Bill opened a sagging backpack and revealed sacks of peas rattling like green hailstones, plus coupons promising free dentures, miniature golf discounts, and one conditional canoe. He arranged everything with surgical tenderness, envisioning international fame, although Molly suspected their eventual documentary would be narrated by embarrassed relatives and disappointed detectives. "Frozen peas and expired coupons, heavy, mysterious, educational, it builds character while we sell the real toys to that fence in Dayton." Molly stared at the plan, then at Bill, then at the getaway tricycle leaning against the wall with one wobbly wheel and delusions of motorsport glory. She sighed, stole his nose, tucked it into her pocket for insurance, and nodded once, which in their partnership constituted a binding emotional commitment. "Fine, but if the pinata fights back, you are on your own, hero, undoubtedly."
created_at
"2026-10-13T10:12:43.741Z"
10/13/2026, 10:12:43 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2163
moderation_latency
(null)
generation_time
31119
tokens_prompt
75
tokens_completion
990
native_tokens_prompt
68
native_tokens_completion
5390
native_tokens_completion_images
0
native_tokens_reasoning
4590
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
0.108072
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886363-yGCGNyA87zWGRGDVg4Zu"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886363-vJH1ULUBZcDXqmv2CEla"
upstream_id
"resp_6ace041c42339e003ab244ea"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace041c42339e003ab244ea"
is_byok
false
latency
911
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.108072
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: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%