NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TANRGEY3PDSAHTRDR79Y42
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
29.2s
Cost:
$0.096032
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.49%
Dialogue to Total Word Ratio
(details)
99.7387%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 peered through the community hall window at a mountain of presents beside a crooked cake, while Bill crouched behind a hedge wearing a bright red clown wig and holding an empty laundry sack like it was treasure. "Do you see them, Bill? Do you see the glorious pile?" "I see a cake shaped like a dinosaur, Molly. I also see thirty children armed with juice boxes." "Ignore the children. Focus on the presents. One of them definitely contains a toy spaceship." "The big one?" "No, Bill, the big one contains socks. It always contains socks. Trust my instincts." "Your instincts told you the museum had no alarms." "That alarm was surprisingly loud for a small museum." "And surprisingly attached to several policemen." Molly adjusted her own clown nose and tried to look dignified, which was difficult because the nose squeaked every time she breathed. "Today will be different. We walk in as entertainment, we smile, we perform, we leave richer." "We cannot juggle, Molly." "We can pretend to juggle. Confidence is ninety percent of juggling." "The other ten percent is catching." "Then we shall drop things charmingly." "What is my character?" "You are Bongo the Magnificent." "And you?" "I am Madame Bubbles, mistress of mystery and balloon animals." "You cannot make balloon animals." "I can make a sausage." "That is not an animal unless the party is very unusual." Inside, a child screamed happily at a pinata, and Bill flinched so hard his wig slipped over one eye. "Explain the plan again, slowly, and without using the word heist." "We enter. We dazzle. You make balloon sausages. I chat beside the present table. The presents quietly join us outside." "Presents do not quietly join anyone, Molly. They crinkle." "Then we cough loudly over the crinkling." "All of us?" "Yes, Bill, synchronized coughing. It is elegant." "It sounds diseased." "It sounds like show business." Molly produced two party hats and placed one solemnly on Bill's wig, as if crowning a very nervous king. A parent inside began leading a conga line, and the present table stood briefly, gloriously unattended on the far side of the room. "Look! The conga has begun! Our moment approaches!" "Molly, my sack has a hole." "Use the hole as a feature. Presents go in, adventure comes out." "That makes no sense." "Neither does Bongo the Magnificent, yet here you are." "What if they ask for a song?" "We sing Happy Birthday very slowly and back toward the door." Bill stared at his shoes, which honked softly. "Tell me honestly, is this revenge because that girl beat you at musical chairs?" "She did not beat me. The chair moved." "You were banned from three parties that summer." "And yet my spirit remained festive." "Then promise me one thing, Bongo." "Anything, Madame Bubbles." "If we get caught, you take the blame." "Deal, as long as we run on three." Molly grinned, squeezed her squeaking nose twice, and together they marched toward the music like the world's least trustworthy entertainment.
created_at
"2026-10-13T09:49:36.665Z"
10/13/2026, 9:49:36 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2261
moderation_latency
(null)
generation_time
29192
tokens_prompt
75
tokens_completion
847
native_tokens_prompt
68
native_tokens_completion
4788
native_tokens_completion_images
0
native_tokens_reasoning
4036
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
0.096032
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791884976-vtaNNGcpruuNbuofw40p"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791884976-GsU6gP0JzkVm0vfCQ2Hn"
upstream_id
"resp_6acdfeb1864b9ebf7662409e"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6acdfeb1864b9ebf7662409e"
is_byok
false
latency
652
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.096032
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
99.49%
Dialogue to Total Word Ratio
Ratio: 70.32%, Deviation: 0.32%
neededClean
false
wordsTotal
502
wordsDialogue
353
99.7387%