NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TATMN8VF48V598J0X27PJX
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
25.1s
Cost:
$0.083472
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9920%
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 garden hedge, peering through binoculars at the bright balloons bobbing above the crowded backyard fence. “We hit the party at noon, when the cake arrives and everyone turns toward the kitchen door,” she whispered, adjusting her ridiculous clown wig. Bill scratched his chin and studied the crumpled map spread across the damp grass between them. “I still think the bouncy castle entrance is safer than the side gate with the noisy latch,” he muttered, tapping one muddy boot nervously against the hedge. Molly rolled her eyes and pointed toward the gift table piled high with shiny wrapped boxes. “Look at that tower, Bill. Ribbons, bows, and probably three bikes hidden under all that glittering paper.” Bill shook his head slowly, watching a small child chase another child with a water pistol. “I agreed to steal presents, Molly, not to dodge armed toddlers soaking every adult in sight today.” Molly grinned and pulled two empty sacks from her backpack, shaking them open with theatrical flourish. “Relax. We dress as entertainers, juggle three oranges, and everyone claps while you quietly load the sacks.” Bill frowned at the oranges rolling around inside her backpack beside rope, tape, gloves, and sandwiches. “Why do we have sandwiches hidden between the rope and the suspiciously professional lockpicking kit again exactly?” Molly shrugged innocently and handed him a cheese sandwich wrapped neatly in brown paper. “Because crime makes me hungry, and you get grumpy, reckless, and loud whenever your stomach starts rumbling.” Bill took a reluctant bite, chewed thoughtfully, and nodded toward the house where music suddenly blasted louder. “Fine, I enter first, distract the parents with balloon animals, and you sneak behind the gift table.” Molly shook her head firmly and wagged one finger under his nose like a stern teacher. “No, you are terrible at balloon animals. Your dogs look like sausages, and your giraffes look haunted.” Bill clutched his chest dramatically, pretending deep offense while secretly agreeing because every previous attempt had failed miserably. “My giraffe was artistic, Molly. The children screamed because they felt overwhelming emotion, not absolute terror.” Molly unfolded the map again and traced their route with a crayon stolen from a restaurant. “You make balloons near the drinks. I slip inside, grab boxes, and pass them through the hedge.” Bill peered again at the backyard, counting adults, children, dogs, gates, windows, and one extremely suspicious grandmother. “That grandmother has watched us for ten minutes. I swear she knows exactly what we are planning.” Molly waved cheerfully at the grandmother, who waved back slowly without blinking or smiling once. “Perfect. She thinks we are early entertainers. Confidence sells the disguise, Bill, so stop looking guilty.” Bill straightened his bowtie, practiced a cheerful smile, and immediately stepped backward into a muddy puddle. “Then we run straight to the van, drive beyond the river, and never juggle another orange again.” Molly nodded, checking her watch carefully. “We move in five minutes. Grab ribbons first, smile constantly, and absolutely no stealing cake.”
created_at
"2026-10-13T09:52:16.564Z"
10/13/2026, 9:52:16 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1600
moderation_latency
(null)
generation_time
25103
tokens_prompt
75
tokens_completion
946
native_tokens_prompt
68
native_tokens_completion
4160
native_tokens_completion_images
0
native_tokens_reasoning
3371
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
0.083472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885136-9epwfJ9ixmhZuJXdOMsl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885136-I1Cp1MElfoe6FNe1b1oG"
upstream_id
"resp_6acdff506d58ee1e40184594"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6acdff506d58ee1e40184594"
is_byok
false
latency
365
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.083472
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
99.98%
Matches word count
n/a
neededClean
false
words
502
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
502
wordsDialogue
251
99.9920%