NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4X5X6J4KYJ8FMKDS5YDKR
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
12.2s
Cost:
$0.006474
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 blueprint across the hood of their dented getaway van, which still smelled faintly of old tacos. The paper was not a bank vault schematic but a crayon drawing taped to a fridge, photographed and enlarged at Staples. The drawing showed a house, a big lopsided cake, and what appeared to be a mountain of presents guarded by stick figures with party hats. Bill squinted through his reading glasses. "So let me get this straight. The target is Timmy Henderson's seventh birthday party?" Molly tapped the mountain of presents with a chipped red nail. It was labeled PRESENTS!!! in aggressive glitter marker. "Not just any party, Bill. Timmy's dad is a distributor for Hyper-Robo-Dino-X toys. Limited edition. Sells for four hundred bucks a pop on eBay. There's gonna be twenty of them in there, untouched, unopened." "And we're stealing from children now? I have standards. Low standards, but they exist." "We are stealing from a very spoiled demographic, which is totally different. Robin Hood stole from the rich. These kids are rich in juice boxes." Bill folded his arms, trying to look principled despite wearing a shirt that said FREE HUGS. "What's the security situation?" "One rent-a-clown, one bouncy castle, and Brenda Henderson, who runs neighborhood watch like it's the CIA. She's our biggest obstacle." Molly traced a line to the side door. "We go in through the side gate during the pin the tail on the donkey distraction. That's at fourteen hundred hours. You will be dressed as the entertainment." "I told you I'm not wearing the clown suit again. It chafes and the kids can smell fear." "You are not the clown. You're Spider-Man. I got you a costume on clearance. The kids love Spider-Man." Bill perked up slightly. "Does it come with web shooters?" "It comes with mild disappointment and stretchy pants. The plan is you cause a diversion, do some flips, maybe let them beat you up a little. Classic Spider-Man stuff. While they swarm you, I slip into the living room and extract the package." "And what if the package is guarded?" "You mean if a seven-year-old is sitting on it?" "What is your contingency for a seven-year-old perimeter defense?" Molly grinned. "I brought Goldfish crackers and a firm talking-to. I'm not above bribery. Also, I have a Paw Patrol Band-Aid for psychological warfare." Bill stared at the crayon blueprint again, at the little X marked where the presents were stacked beside what looked like a very angry dog. "Is that a guard dog or did Tommy draw his mom?" "That's Buttons the Pomeranian. He has three teeth and a deep-seated grudge. We leave him alone and he leaves us alone. Treaty of 2022, still stands." Molly rolled up the blueprint. "This is our most sophisticated job yet. In and out, no casualties, maximum plunder. We take the dinos, we leave the socks and educational books." Bill sighed and zipped up the Spider-Man suitcase. The mask had one eye slightly higher than the other. "Fine. But if I get stuck in the bouncy castle again, you have to come get me. Last time I was in there for forty-five minutes and a kid named Jayden tried to recruit me for his gang." "You got this. Remember, you are not just a thief in spandex. You are a friendly neighborhood thief in spandex." "That's supposed to be comforting?" Molly opened the van door and honked twice, which was their official heist start noise. "Let's go steal a childhood."
created_at
"2026-07-25T17:24:29.742Z"
7/25/2026, 5:24:29 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5781
moderation_latency
(null)
generation_time
12029
tokens_prompt
75
tokens_completion
876
native_tokens_prompt
225
native_tokens_completion
1457
native_tokens_completion_images
0
native_tokens_reasoning
674
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
0.0064735
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f14e7ee8414154024913"
is_byok
false
latency
244
model_permaslug
"meta/muse-spark-1.1-20260709"
provider_name
"Meta"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785000269-g9yX5VbduOmZZbQyC0I3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000269-3J42HirIYBsggmx0cYxC"
upstream_id
"resp_6a64f14e7ee8414154024913"
total_cost
0.0064735
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
584
0.00%
Dialogue to Total Word Ratio
Ratio: 69.38%, Deviation: 39.38%
neededClean
false
wordsTotal
601
wordsDialogue
417
0.0000%