NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M753B9AW8GZ3977FHDMBHWTB
Run Details
Model:
Muse Ember (Reasoning, Max)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
17.3s
Cost:
$0.005562
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
44.93%
Dialogue to Total Word Ratio
(details)
72.4664%
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
Rain hammered the alley behind the bakery while Molly sketched the Johnson backyard on a damp napkin and Bill studied it like a complicated tax form in silence. "Bill, the Johnsons are throwing a party for their twins tomorrow afternoon in the backyard." Bill nodded and replied. He pointed toward the twins' crayon drawing taped to the bakery window and then toward the pile of presents glimpsed through their garden gate. "Great, presents will be stacked by the fence and parents will be distracted by cake." Molly tapped the napkin with a chewed pencil and grinned proudly. She had already rented clown costumes from a dubious shop selling sticky wigs and one rubber chicken. "Exactly. We will wear those ridiculous clown costumes and walk right past the gate." Bill crossed his arms and shook his head firmly. He remembered the shoes, the toddler, and the unsettling determination in that tiny tax inspector's eyes at the party. "I am not wearing a clown costume. Last time I wore one, a toddler annexed my shoes." Molly rolled her eyes and lowered her voice conspiratorially. Outside a delivery van reversed slowly, honking musical beeps like an old birthday song played backwards in the rain. "Bill, nobody will suspect clowns. We will grab every box, bag, and bicycle." Bill frowned at the sleeping dog beside the gift table in his memory. That dog once chased a mailman three blocks and chewed every envelope it found proudly. "Bicycles are heavy. How are we getting those past the pinata and the bouncy castle?" Molly unfolded a small wagon from behind the bakery bins and tested its squeaky wheels with professional admiration. The wagon smelled faintly of onions, glue, and old glory. "Simple. I will create a diversion by juggling rubber ducks while you load the wagon." Bill winced and rubbed his ankle in sympathy. He had limped since the chainsaw incident, which Molly called character building and Bill called grounds for resignation quite loudly. "Your juggling is terrible, Molly. You dropped a chainsaw on my foot last Tuesday." Molly spread her arms wide like a magician unveiling a mediocre trick. She pictured parents chasing each other with cake, confetti, and one enthusiastic uncle wearing paper crowns. "That was practice. Tomorrow we will be heroes of the gift table and villains of arithmetic." Bill checked his watch, then the sky, then his watch again as if time might reconsider. He agreed because the plan was absurd enough to work tomorrow afternoon. "Fine. Midnight? No, two o'clock, when the magician is busy sawing the couch in half." Molly clapped once, startling a pigeon into flight. She folded the napkin, tucked it into her pocket, and began humming a tune about stolen presents and squeaky wagons. "Perfect." Bill stood, brushed crumbs from his coat, and hoisted the wagon like a knight claiming a questionable quest. Molly adjusted her clown nose, winked at the rain, and declared their rehearsal officially complete with theatrical, deeply unnecessary applause amid puddles and pigeons.
created_at
"2026-11-11T10:44:35.819Z"
11/11/2026, 10:44:35 AM
model
"meta/muse-ember-20261109"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1878
moderation_latency
(null)
generation_time
17285
tokens_prompt
75
tokens_completion
781
native_tokens_prompt
69
native_tokens_completion
11110
native_tokens_completion_images
0
native_tokens_reasoning
10439
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
0.0055619
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794393875-21BPZ8SJVAdKw1MpJ2jw"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794393875-MJmfGGcewmnht7o9QVED"
upstream_id
"resp_6af44714914a65798605417e"
provider_responses
0
endpoint_id
"ea8469c2-ddf8-4985-8cf2-f5dc7e63e14c"
id
"resp_6af44714914a65798605417e"
is_byok
false
latency
1161
model_permaslug
"meta/muse-ember-20261109"
provider_name
"Meta"
status
200
total_cost
0.0055619
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
44.93%
Dialogue to Total Word Ratio
Ratio: 34.00%, Deviation: 4.00%
neededClean
false
wordsTotal
500
wordsDialogue
170
72.4664%