NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBKPBWH0QHP9W3JRABF9CF
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
21.5s
Cost:
$0.078432
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 a crayon map across the kitchen table while Bill balanced a party hat on his head. She tapped the clown drawing and whispered, "We hit the party at noon tomorrow when the clown arrives and everyone looks away laughing." Bill nodded solemnly then sneezed into a bowl of glitter and replied, "I love clowns but I hate children so this plan already feels emotionally complicated for me personally." Molly rolled her eyes and slid the present pile drawing toward him firmly before saying, "Focus Bill because eight year olds guard presents like dragons guard gold in fairy tales." Bill considered both costumes hanging crookedly behind the door and asked, "Do I wear the dinosaur costume or the pirate costume for maximum stealth and style points?" Molly answered instantly while tying tiny gift bows around her fingers for practice and added, "Pirate obviously since dinosaurs attract hugs and pirates attract respectful fear from small sugar fueled witnesses." Bill patted his stomach with genuine concern spreading across his face and confessed, "What if they offer me cake and I forget the mission entirely mid bite again?" Molly mimed dragging something heavy across the floorboards then grinned and promised, "Then I drag you out by your fake hook while pretending you are party entertainment gone wrong." Bill rubbed his chin beneath an imaginary beard and thoughtfully declared, "Genius but we still need a distraction bigger than juice boxes and louder than twenty recorders." Molly pulled a balloon from her sleeve like a magician and explained, "We release fifty balloons outside and shout that a unicorn escaped into the neighbor's yard nearby." Bill covered his ears remembering last summer fair disaster very clearly and muttered, "Kids love unicorns almost as much as they love screaming directly into my ears at close range." Molly traced a bold red escape route through garden gnomes and whispered, "While they chase balloons we grab the gift table and roll it straight through the side gate." Bill imagined mud cake frosting disaster scenes unfolding rapidly and worried aloud saying, "That table has wheels hopefully otherwise we become two sweaty pirates dragging furniture across wet grass loudly." Molly kicked the table leg gently watching it glide forward and teased, "I checked yesterday and the table rolls beautifully unlike your last getaway scooter with one wheel missing." Bill defended his dignity while polishing a plastic hook with exaggerated pride and answered, "That scooter had character and speed and only mildly betrayed me downhill near the police station." Molly scanned her notes about guards snacks exits and sleeping toddlers then warned, "No police this time just parents with cameras and one grandmother who looks suspiciously strong and alert." Bill shivered despite the warm afternoon sunlight pouring through curtains and whispered, "Grandmothers terrify me most honestly." Molly folded the map into his pirate pocket patted it twice and they shook hands solemnly before tiptoeing out together to rehearse balloon releases behind the garage before lunch tomorrow morning without waking anyone quietly.
created_at
"2026-10-13T10:05:57.508Z"
10/13/2026, 10:05:57 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1774
moderation_latency
(null)
generation_time
21476
tokens_prompt
75
tokens_completion
903
native_tokens_prompt
68
native_tokens_completion
3908
native_tokens_completion_images
0
native_tokens_reasoning
3203
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
0.078432
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885957-LValL9XLDLsQTwOPMTQ0"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885957-3ySbmzIMJb7bGebFUzNV"
upstream_id
"resp_6ace02864802b254abf54752"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace02864802b254abf54752"
is_byok
false
latency
649
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.078432
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%