NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M754GGE7BKTFTXHTH4AFQPKS
Run Details
Model:
Muse Ember (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
10.9s
Cost:
$0.003392
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 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
The van hissed outside the warehouse as Molly zipped her black jacket and checked the rope coiled beside the door. "Bill, are you double checking the guest list or are you asleep again?" she said. "I'm awake," Bill said. "I have the list right here and it is huge." "How many kids are coming then, genius, and where exactly are we parking?" Bill spread the paper across a crate beside a carton of cake candles and party hats. "Twenty kids," he said. "Twenty five presents, at least, piled underneath that table." "Twenty five? That is more than enough to sell back at the pawn shop tomorrow." She tapped the map with one gloved finger and grinned at the garden gate marked in red ink. "The garden gate," she said. "We slip in while the parents are busy with games." "And the dog?" Bill asked. "The neighbor said that dog never sleeps." "The dog is deaf as a post," Molly said. "I checked last Tuesday with steak." "Steak?" Bill said. "You befriend every guard animal with steak." "Works every time," Molly said. "Even the one at Saint Mary's bakery." Bill nodded and stuffed the rope into a sack that already held gloves and a crowbar. "Okay, okay," he said. "We go in at five, grab the pile, and run." "What about the clown?" Molly asked. "That clown saw me last time." "The clown?" Bill said. "He works for balloons and tips only." "He saw my face and my jacket, Bill," Molly said. "He will remember." "Then we wear masks," Bill said. "And we bring extra balloons too." Molly laughed and tossed him a mask shaped like a cheerful frog face. "Perfect, frog master," she said. "You can be the lookout frog." "Lookout frog?" Bill said. "I wanted the treasure chest duty." "Treasure chest duty is grabbing gifts while everyone sings," Molly said. "You sing badly." "I sing fine when nobody listens," Bill said. "And the parents will be busy clapping." "Fine, you carry the big box, and I will run interference with cake." Bill sighed and lifted the sack while Molly unlocked the van door with a loud click. "Interference with cake?" Bill said. "That plan caused the last disaster." "The last disaster was your fault," Molly said. "You dropped the cake." "I dropped it because the sprinkles were slippery," Bill said. "Sprinkles are dangerous." "Right, slippery sprinkles, very dangerous," Molly said. "Now get in the van." "Van is ready," Bill said. "But we still need one more thing for tonight." "What thing?" Molly said. "We have rope and steak and masks already." "The birthday song," Bill said. "We need it timed exactly right." "Timed?" Molly said. "Why does a song matter, Bill?" Silence. "Listen, we time our grab for the second verse, because the parents will be filming, the kids will be screaming, and nobody will see two frogs sneaking past the balloons toward the car before the magician returns with more juice boxes and a very loud kazoo tonight."
created_at
"2026-11-11T11:04:55.5Z"
11/11/2026, 11:04:55 AM
model
"meta/muse-ember-20261109"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1698
moderation_latency
(null)
generation_time
10904
tokens_prompt
75
tokens_completion
866
native_tokens_prompt
69
native_tokens_completion
6771
native_tokens_completion_images
0
native_tokens_reasoning
5963
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
"default"
usage
0.0033924
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794395095-ubXNQ4XrZYxvMVLXvarE"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794395095-iJkeLRNqXB6etRuSH21y"
upstream_id
"resp_6af44bd8394d507592ae42bc"
provider_responses
0
endpoint_id
"ea8469c2-ddf8-4985-8cf2-f5dc7e63e14c"
id
"resp_6af44bd8394d507592ae42bc"
is_byok
false
latency
740
model_permaslug
"meta/muse-ember-20261109"
provider_name
"Meta"
status
200
total_cost
0.0033924
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: 70.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
350
100.0000%