NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5H6W71CPZZ6Y9B2HDFK7B
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
30.4s
Cost:
$0.019852
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
51.39%
Dialogue to Total Word Ratio
(details)
75.6869%
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
The church basement smelled like wet cardboard and leftover frosting. Molly spread the blueprint across the communion table. "Okay, so Timmy Turner's seventh birthday is at two. That's our window." Bill squinted at the scribbled map. It was drawn in crayon. Three Xs marked the present table, the juice boxes, and what was labeled dragon. "You stole a five-year-old's invitation to get this intel. I want that noted for our professional records." Molly tapped the present table with a french fry. She had stolen the fry from somewhere else. "It's reconnaissance. Besides, the invitation said no gifts under twenty bucks. Kids these days are ruthless capitalists." Bill folded his arms. His security guard disguise was just a yellow vest that said EVENT STAFF on it in sharpie. "What's the actual plan? We can't just walk in and take a pile of Bluey toys." Molly grinned. She produced two smaller vests from her backpack. One said JUNIOR EVENT STAFF. "We walk in and take a pile of Bluey toys. But professionally. With lanyards." Bill stared at the vest that would barely fit his left leg. Outside, a van full of screaming kids pulled up early. "That's the decoy van. Timmy's mom hired a magician. We're gonna let him do the hard work." Molly explained how the magician would make a distraction loud enough that two grown adults in tiny vests could wheel out presents in a laundry hamper. "So your master plan is hope a clown is annoying enough to cover a felony?" He wasn't a clown. Molly had checked. He was a magician who specialized in making juice disappear. Unexplained liability. "He is absolutely a clown. And this is a new low, Molly. Even for us. Stealing from children?" She looked offended. She pulled out a clipboard. On it, she had listed resale values. Paw Patrol headquarters was apparently worth forty. "We are not the villains. The parents who spend fifty bucks to impress other parents are the villains. We are redistributing plastic." Bill considered this. The basement door banged open upstairs, and the sound of Happy Birthday played aggressively off-key on a ukulele. "I still think we need an exit strategy. What's phase two, once every five-year-old starts screaming?" Molly zipped the blueprint back up. She pulled on her vest. It rode up to her ribs. "We cry too. No one suspects two adults crying at a kids party. They assume divorce. Then we roll the hamper out slow." The plan was terrible. It was also the only plan that fit on a stolen invitation. Bill put on his vest anyway. "For the record, if we get tackled by a mom, I'm telling them it was all your idea." Upstairs, the magician announced he would now make all the parents' patience disappear. It was time. "Let's go steal some joy. Or toys. Same thing, really." They pushed the hamper toward the stairs, trying to look like they belonged. "You push faster, junior, or I'm leaving you here to become the entertainment."
created_at
"2026-07-25T17:35:26.093Z"
7/25/2026, 5:35:26 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
26381
moderation_latency
(null)
generation_time
30349
tokens_prompt
75
tokens_completion
751
native_tokens_prompt
225
native_tokens_completion
4605
native_tokens_completion_images
0
native_tokens_reasoning
3930
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
0.0198525
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f3ded198f01200db407c"
is_byok
false
latency
420
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-1785000926-z7Dc5FbR4RSsmtEoJpHU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000926-Qay6owMyBxwLDozhE1wW"
upstream_id
"resp_6a64f3ded198f01200db407c"
total_cost
0.0198525
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
99.98%
Matches word count
n/a
neededClean
false
words
502
51.39%
Dialogue to Total Word Ratio
Ratio: 46.35%, Deviation: 3.65%
neededClean
false
wordsTotal
507
wordsDialogue
235
75.6869%