NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBN57MGXWJD85KE30FBWCS
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
26.3s
Cost:
$0.119952
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
Molly spread the birthday party invitation across the kitchen table like architectural plans for a bank vault. Rain tapped the windows while Bill leaned forward, squinting at the glittery unicorns and trying to look like a criminal mastermind instead of a man wearing mismatched socks. "This is our easiest score ever," Molly said. Bill nodded solemnly and adjusted his imaginary tie, although he actually wore a hoodie decorated with pizza stains from three separate decades. "We walk in, grab the presents, and disappear before cake," he said. Molly tapped the address printed beneath a rainbow. "That confidence would impress me more without jelly on your chin," she replied. Bill wiped his chin with theatrical dignity and studied the invitation again. "Timmy turns seven at noon," Bill read. Outside, thunder muttered beyond the rooftops. Inside, their kettle clicked off, unnoticed. "Seven year olds cannot identify suspects reliably," Molly said. The plan required costumes, confidence, timing, and one extremely large laundry bag disguised as a decorative sack. "We need disguises nobody questions," Molly announced. Bill brightened instantly, which historically meant something terrible was about to be suggested with complete sincerity. "Clowns," he said. "Children love clowns, parents expect clowns, and nobody asks clowns questions." Molly stared at him until his smile developed visible cracks. "Children fear clowns, parents photograph clowns, and everyone remembers a six foot clown stealing bicycles," she said. Bill considered this while doodling a clown inside a getaway car. The drawing looked alarmingly cheerful and legally incriminating. "Fine, magicians then," he offered. Molly shook her head. "Magicians carry suspicious boxes and wear capes with pockets," she explained. Bill wrote magicians down and underlined it twice, despite neither of them knowing a single magic trick beyond making rent money vanish. "I can pull a rabbit from your handbag," he said. Molly glanced toward her handbag, which contained receipts, mints, lockpicks, and absolutely no rabbit. "That is a guinea pig wearing ears, and Kevin hates show business," she said. Kevin, their neighbour's pet, had bitten Bill during two rehearsals and one regrettable attempt at showmanship. "Kevin is jealous of my natural stage presence," Bill said solemnly. Molly moved a chess piece across the street map to represent their van. It was a bishop, because Bill had lost every knight down various sofas. "We arrive at eleven forty during musical statues," Molly said. Bill moved a peanut to mark the garden gate. "While adults watch frozen children, we empty the present table," he said. Molly placed a bottle cap beside the peanut and frowned at their growing edible invasion force. "Unless someone brings a pony," she warned. Bill stopped smiling for the first time since breakfast. Ponies introduced unpredictability, teeth, and an audience of screaming amateur photographers. "No plan survives contact with a pony," Bill whispered. Molly wrote pony contingency in red ink, then underlined snacks twice for reasons she refused to explain. "We steal presents, avoid ponies, and never perform again," Bill said. Outside, thunder applauded their absolutely terrible wonderful plan.
created_at
"2026-10-13T10:06:45.501Z"
10/13/2026, 10:06:45 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1822
moderation_latency
(null)
generation_time
26303
tokens_prompt
75
tokens_completion
943
native_tokens_prompt
68
native_tokens_completion
5984
native_tokens_completion_images
0
native_tokens_reasoning
5191
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
0.119952
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886005-wCs0qNFxdnl5i8kNIttg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886005-S0NkOXyCfsjCPu28ylLQ"
upstream_id
"resp_6ace02b5308835e283484b81"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace02b5308835e283484b81"
is_byok
false
latency
506
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.119952
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%