NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBMAA6Z4ANXF2V8Y9M51T9
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
23.5s
Cost:
$0.073352
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9961%
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 crouched behind the hedge outside the Wilson house, binoculars pressed to her eyes, watching a clown wrestle a balloon giraffe while twenty sugar-fuelled children screamed like tiny air raid sirens. Bill lay beside her in the mulch, wearing a ghillie suit he had bought for a bank job in Scotland and refused to ever leave at home without. A garden gnome stared at them judgingly. "Okay, birthday cake is at fourteen hundred hours, presents stacked by the patio, zero security except Brenda." Molly whispered into a headset she did not need because Bill was six inches away. "Brenda is the grandmother with the handbag that knocked out a traffic warden, remember? I respect Brenda." Bill said, scratching mulch from his ear and trying not to sneeze on a daisy. "Focus. You go in as entertainment. I slip round back, grab the loot, meet at the inflatable castle." She unzipped a duffel bag revealing a unicorn costume, a magician's cape, three water pistols, and enough party poppers to stage a small revolution in a bouncy suburb. Bill stared at the unicorn head as if it had personally betrayed him during a previous life. "I am not wearing that. Last time I wore fancy dress, Interpol got photographs and a nickname." The nickname had been Sparklehoof, and it still appeared on two watchlists and one very flattering fan blog run out of Belgium. "Wear it or explain to Big Sal why we retired on a stolen tricycle and six colouring books." Inside the garden, a piƱata burst prematurely, scattering sweets and causing a diplomatic incident among the under-sevens. Two dads fought politely over the last sausage roll while the birthday boy, Timmy, declared himself king and annexed the trampoline. Molly checked her watch, her burner phone, and the escape route she had drawn on a napkin in ketchup. "Fine, but if anyone climbs on my back, I am charging them and keeping the deposit this time." Bill pulled the costume over his head, immediately walked into the hedge, reversed, apologised to the gnome, and tried again with what dignity a six-foot unicorn in mulch could reasonably retain on a Saturday afternoon. "Beautiful. You look magical, terrifying, and slightly damp. Now trot in when the clown starts the musical statues." She handed him a wand made from a loo brush and glitter glue. "And if the kids ask for balloon animals, what then? I only know sausage, snake, and smaller sausage." From beyond the fence came the opening bars of musical statues, a song so cheerful it should have been illegal in twelve countries. Children froze mid-scream. The clown froze too, possibly from fear. Molly gave Bill a firm shove between the shoulder blades and watched him canter through the side gate to thunderous applause. "Go steal childhood, Sparklehoof, but leave Timmy the dinosaur book." She slipped toward the shiny presents, sack ready, conscience conveniently quiet, while Bill accidentally started a very joyful conga line of delighted screaming small children behind him.
created_at
"2026-10-13T10:06:17.936Z"
10/13/2026, 10:06:17 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2241
moderation_latency
(null)
generation_time
23423
tokens_prompt
75
tokens_completion
852
native_tokens_prompt
68
native_tokens_completion
3654
native_tokens_completion_images
0
native_tokens_reasoning
2910
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
0.073352
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885977-DOpMt9B4GKX53Iem9clW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885977-U7XXec0E1UvW43NEVYDT"
upstream_id
"resp_6ace029af782a50e4f6f4ed0"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace029af782a50e4f6f4ed0"
is_byok
false
latency
510
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.073352
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
99.99%
Dialogue to Total Word Ratio
Ratio: 29.96%, Deviation: 0.04%
neededClean
false
wordsTotal
504
wordsDialogue
151
99.9961%