NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4Q6X3BPAD78YQB705YRTP
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 31s
Cost:
$0.029435
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.9017%
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
Rain hammered the stolen van as Molly unfolded a crayon map of Sunny Sprouts Community Center while Bill adjusted his squeaky clown nose nervously again. "Okay Bill, Timmy Thompson turns seven at three, and his greedy little guests have already piled presents mountain-high in the cake room so focus please." Bill stared through the foggy windshield at bouncing balloons and shuddered, tugging the rainbow wig that smelled like old popcorn and bad decisions very loudly. "Molly, are we really stealing from a children's party? I signed up for banks, museums, maybe casinos, not juice boxes and tiny chairs you know?" Molly snorted and tapped the map with a plastic pirate sword, pointing dramatically at the side door propped open for the pizza delivery guy earlier. "Exactly, nobody questions a clown carrying a giant gift bag. You distract them with balloon animals while I grab the loot, simple and clean okay?" Bill gulped and pulled out three limp balloons, twisting them into something that looked less like a dog and more like a sad intestine somehow. "I cannot make balloon animals, Molly. Last time I tried, a toddler cried, a mime quit, and I got banned from Chuck E Cheese forever." A chorus of off-key singing erupted inside as Molly checked her watch, slipped on fake mustaches, and handed Bill an empty Santa sack quickly now. "Happy birthday starts in five minutes, so we move during cake time. Sugar crash equals perfect cover, nobody watches presents while frosting flies everywhere trust." Bill peered at the guest list taped to the dash, his face paling as he read the ominous warning written in glittery purple crayon slowly. "It says entertainment by Mad Madge the Maniac Clown. Molly, she once bit a magician. Bit him. Do we really want to compete with that?" Molly grinned wickedly, pulling two water pistols from her backpack and loading them with apple juice, ready for absolute sugary chaos and glory today pal. "Madge is yesterday's news. Squirt the kids, cause a sticky stampede, yell surprise inspection, then haul every shiny box to the van fast got it?" Thunder rumbled as Bill practiced his clown laugh, which sounded like a dying goose honking into a traffic cone during rush hour painfully loud truly. "Fine, but if I get tackled by a five-year-old ninja turtle, you owe me half your cut plus therapy and new pants immediately deal Molly?" Molly shook his hand solemnly, then pointed at the parking lot where parents unloaded towers of brightly wrapped boxes tied with enormous bows just gleaming. "Deal. Remember, we only take presents, not candy, not cake. Well, maybe one cupcake for courage. For morale. For professional thieves like us agreed buddy?" They bumped fists as the party lights flickered on, children's laughter spilling out while the van door creaked open toward destiny and mischief tonight finally. "Let's rob this birthday, partner. Operation Diaper Loot is go, though I still feel terrible about stealing Timmy's dinosaur scooter, honestly really truly sorry kid."
created_at
"2026-09-03T08:03:46.222Z"
9/3/2026, 8:03:46 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3884
moderation_latency
(null)
generation_time
91222
tokens_prompt
75
tokens_completion
785
native_tokens_prompt
68
native_tokens_completion
6906
native_tokens_completion_images
0
native_tokens_reasoning
6236
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
0.0294355
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422626-1oUAF2fLac9eZPvM0yNl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422626-Q9zPY0mwqlWDkv4w8t4n"
upstream_id
"resp_6a9929e299255f01c2724e56"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a9929e299255f01c2724e56"
is_byok
false
latency
836
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.0294355
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
99.80%
Dialogue to Total Word Ratio
Ratio: 50.20%, Deviation: 0.20%
neededClean
false
wordsTotal
504
wordsDialogue
253
99.9017%