NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4QN9TBCT1QHHV15EPA6MK
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
39.0s
Cost:
$0.029037
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
97.20%
Dialogue to Total Word Ratio
(details)
98.5988%
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
The bakery van idled two houses from the Hendersons'. Inside, Molly spread a crayon map while Bill untangled disguises. The target was a bouncy castle backyard with forty presents piled on a superhero tablecloth. "Okay, so the house is full of six-year-olds. How hard can it be?" Bill stared at the map, which was mostly stick figures and what appeared to be a juice stain shaped like Texas. "Molly, last time you said that we ended up in a ball pit for three hours." Molly did not look up. She was busy highlighting the present table with a glitter marker she had stolen from her niece. "That was reconnaissance. This is a highly sophisticated present extraction." She said it with complete confidence, the same confidence she used when explaining how they would steal the mayor's toupee. Bill had learned not to question it too loudly. "It's a kid's birthday party. At two PM. With a clown." He pointed at the surveillance photo taped to the visor. It showed a grinning clown holding a screaming child upside down. The clown's name tag read Chuckles. Chuckles did not look like he chuckled. "Exactly. No one expects professional thieves at a clown party. It's perfect." Molly grinned and tapped the bouncy castle on the map. Her plan was insane, which in their line of work meant it had a sixty percent chance of working, which was better than average. "What about the mom? Linda? She bench presses minivans." Bill flipped over the intel sheet Linda Henderson had compiled for parents. It was laminated and terrifying. It listed allergies, emergency contacts, and a handwritten note that said no gifts under twenty dollars. "We distract her with small talk and juice boxes. You love juice boxes." The van smelled like frosting and poor decisions. Molly reached into the back and produced two oversized rainbow wigs that shed glitter when touched. Bill sneezed. "I have a plan. We go as entertainers. I'm Mr. Balloons." He held the wig at arm's length like it might detonate. It left a trail of sparkles on his black heist gloves, ruining his intimidating aesthetic completely. "And I'm what, Mrs. Pin-the-Tail?" Molly started braiding her wig while simultaneously eating a stolen cupcake from the bakery stash. This was her thinking face, which Bill found deeply concerning and slightly crumby. "You're my lovely assistant, The Magnificent Molly. You steal presents while I twist poodles." She presented her proposal as if approved. Bill stared at the sketch of himself wearing squeaky shoes and a flower that squirted water. He hated it. "Fifty percent cut then, since I'm doing the actual stealing?" He did math that did not favor him. Molly already pocketed his extra juice box. "Sixty forty. I have to wear the giant shoes." Bill sighed, pulling on the giant shoes. They squeaked mournfully, as if embarrassed for him. "Fine. But if that clown looks at me funny, I'm stealing his tiny car too." Molly grinned, adjusting her glittery badge. "Deal." "Deal."
created_at
"2026-07-25T17:21:28.899Z"
7/25/2026, 5:21:28 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
36020
moderation_latency
(null)
generation_time
38767
tokens_prompt
75
tokens_completion
755
native_tokens_prompt
225
native_tokens_completion
6766
native_tokens_completion_images
0
native_tokens_reasoning
6072
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
0.02903675
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f09927b824fb7e714eed"
is_byok
false
latency
225
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-1785000088-Jt0TS3McORWV79udbmjy"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000088-Yte89Tq09vhoGytNPhAm"
upstream_id
"resp_6a64f09927b824fb7e714eed"
total_cost
0.02903675
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
100.00%
Matches word count
n/a
neededClean
false
words
500
97.20%
Dialogue to Total Word Ratio
Ratio: 30.75%, Deviation: 0.75%
neededClean
false
wordsTotal
504
wordsDialogue
155
98.5988%