NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD77SCB4FB3VRCTMNF54VQC
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
9.8s
Cost:
$0.005162
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
35.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
17.5022%
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
Molly paced a tight circle around the kitchen table while Bill tried to balance a juice box on his head. "Okay, so you're absolutely sure about this target?" Molly said. "One hundred percent. My nephew had his birthday there last week. The haul was legendary," Bill said. "It's a children's party, Bill. We're supposed to be high-class art thieves. We stole the mayor's toupee right off his head." "And now we're diversifying. Listen, have you seen what kids get these days? It's not just crayons and socks anymore," Bill said. "What is it then? Gold bars wrapped in dinosaur paper?" "Better. One kid got a tablet, a remote-control car that goes fifty miles an hour, and a gift card with two hundred bucks on it. All in one pile. Unattended," Bill said. "Unattended because there's a clown and a bouncy castle keeping twenty sugar-crazed six-year-olds busy. That's security you can't buy." "Exactly, which is why we need a plan. A solid, professional, sophisticated plan," Bill said. Molly stopped pacing and pointed at him. "Fine. What's your brilliant, sophisticated plan for robbing a bunch of six-year-olds?" "We walk in with presents," Bill said. "We walk in with presents to steal presents. Genius. What's inside our presents?" "Nothing. They're empty. It's misdirection. We put them down, we pick other ones up. Classic swap," Bill said. "That's not classic anything. That's just showing up empty-handed and leaving much worse. What if someone asks who we are?" "We say we're the entertainment. I'm Mr. Balloons, you're Mrs. Balloons," Bill said. "I am not Mrs. Balloons. I have a reputation. Also, we don't know how to make balloon animals." "We don't need to. We just need to look like we belong until the cake comes out. Everyone watches the cake. That's when we move," Bill said. "And how exactly do we carry out twenty-seven brightly wrapped presents without anyone noticing? Did you bring the getaway van for this?" "I brought my sister's minivan. It has stick-on flames and a car seat that says PRINCESS on it. Very intimidating," Bill said. Molly buried her face in her hands. "This is the worst idea you've ever had and you once tried to rob a bank during a police charity tour." "This is better! Low risk. No alarms. No lasers. Just juice boxes and small humans who will be too busy crying because someone got more frosting," Bill said. "They're going to remember us. Kids never forget. We're going to be the villains in someone's therapy story for the next twenty years." "Or we're going to be rich. Well, rich-ish. Rich enough to finally buy that laser cutter you wanted," Bill said. Molly looked at the juice box that had fallen off Bill's head and was now leaking onto the floor. "If we do this, I want the big one with the dinosaur paper. And we are writing apology cards afterwards," Molly said. "Deal. And we get to eat the cake on the way out. For cover," Bill said. "We are not eating stolen cake from children. Okay, maybe just a little slice for the road."
created_at
"2026-07-25T18:05:14.515Z"
7/25/2026, 6:05:14 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4035
moderation_latency
(null)
generation_time
9549
tokens_prompt
75
tokens_completion
766
native_tokens_prompt
225
native_tokens_completion
1165
native_tokens_completion_images
0
native_tokens_reasoning
472
native_tokens_cached
64
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
0.0051621
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64fada4685d6c7295844d6"
is_byok
false
latency
402
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-1785002714-mjcje7uBW6jBJ581gvyV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002714-ZVinNTz5dtmqlUL1aU8L"
upstream_id
"resp_6a64fada4685d6c7295844d6"
total_cost
0.0051621
cache_discount
0.0000704
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
35.00%
Matches word count
n/a
neededClean
false
words
518
0.00%
Dialogue to Total Word Ratio
Ratio: 84.66%, Deviation: 14.66%
neededClean
false
wordsTotal
528
wordsDialogue
447
17.5022%