NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5HBPS5CYPC34SHZD0ATY0
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
39.0s
Cost:
$0.026287
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
98.56%
Dialogue to Total Word Ratio
(details)
99.1513%
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 smelled like stale pizza and bad decisions. Molly spread the blueprints across the dashboard. "Okay, walk me through this again. We're stealing from a five-year-old?" Bill squinted at the crayon drawing labeled TOP SECRET BIRTHDAY FORTRESS. "It's not about the kid, Bill. It's about the principle. And the presents. Do you know how much a Bluey plush costs right now?" He sighed, adjusting his oversized clown nose. "Molly, last week you said we'd never stoop to piƱatas. And now we're robbing a bounce house?" Molly tapped the giant X marked PRESENT MOUNTAIN. The blueprint was clearly just the invitation with sword doodles added. "That was before I saw the gift list. Little Timmy's getting a Nintendo Switch, a pile of LEGOs, and apparently a live pony. We flip the pony alone and we're retired." Bill stared at her, then at the clown shoes that didn't fit. "First of all, there is no pony. His mom wrote pony-themed party. Second, how do we even get past the parents?" Molly grinned and pulled two tiny vests from a bag. "Easy. We are the entertainment. You are Buttons the Sad Clown. I am Sparkles the Slightly More Optimistic Clown. We walk in, we do balloons, we leave with the loot." Bill held up the vest that read OFFICIAL GIFT GUARD. "This says gift guard. That's suspicious. Also, where did you get a van that says Free Cupcakes?" She honked the horn and it squeaked like a rubber chicken. "Borrowed it from my cousin. Look, security is light. One mom with a whistle, two dads arguing about juice boxes, and a teenager on his phone who is supposed to be supervising. We just need to distract them for ninety seconds." Outside, children screamed and a bounce house wobbled dangerously in the wind. "Ninety seconds to steal twenty presents? That's insane. And immoral. And logistically, how are we carrying a LEGO Death Star out without Timmy noticing?" Molly zipped up her jumpsuit, revealing hidden pockets everywhere. "With our super secret tool. The present trash bag. We say we're helping clean up. Parents love clean up. No parent has ever questioned a clown with a trash bag. It's clown business." Bill looked at his reflection and sighed deeply again. "Okay, but if we get caught, I'm blaming the clown nose. And if there's actually a pony, I'm riding it out of there. Like a getaway horse." Molly high-fived him, leaving glitter on his cheek. "Deal. Now put on your big shoes, partner. We have a birthday to ruin and enough gift cards to buy that pizza van you love." They opened the van doors as Happy Birthday started playing off-key nearby. "One question. What if Timmy cries?" "Then we give him a balloon animal and steal faster." They waddled toward the yard. "Remember, act natural. No one suspects clowns bearing trash bags and bad intentions." "And Bill, try not to befriend the kids this time." "No promises. They get me."
created_at
"2026-07-25T17:35:31.042Z"
7/25/2026, 5:35:31 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
35571
moderation_latency
(null)
generation_time
38871
tokens_prompt
75
tokens_completion
737
native_tokens_prompt
225
native_tokens_completion
6119
native_tokens_completion_images
0
native_tokens_reasoning
5436
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
0.026287
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f3e3a6a1c83f7d5d4ec6"
is_byok
false
latency
408
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-1785000931-q3TsHOHtVHShyRBWu44H"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000931-MKHMGueb9MTycpmsNR7j"
upstream_id
"resp_6a64f3e3a6a1c83f7d5d4ec6"
total_cost
0.026287
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
99.74%
Matches word count
n/a
neededClean
false
words
496
98.56%
Dialogue to Total Word Ratio
Ratio: 69.46%, Deviation: 0.54%
neededClean
false
wordsTotal
501
wordsDialogue
348
99.1513%