NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD859DQ5CBP9E40BBHZBA3C
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
30.4s
Cost:
$0.022262
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
66.22%
Dialogue to Total Word Ratio
(details)
83.1091%
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 blueprints across the sticky diner table. They were not of a bank, but of the Hendersons' backyard, complete with a bouncy castle and a table labeled GIFTS. Bill stared with reverence. "Bill, remind me again why we're robbing a six-year-old's birthday party?" He tapped the juice box station with a french fry. "Because, Molly, last week you said we needed a low-risk job with high emotional payoff." Molly squinted at him over her coffee. The plan had started as a joke after their last job lifting copper pipes from an abandoned car wash had gone sideways. Now Bill had laminated invitations. "I meant volunteering at a soup kitchen, not stealing Paw Patrol toys from Timmy!" Bill nodded solemnly, as if stealing Paw Patrol toys was a moral gray area he had long contemplated during his career of stealing car stereos and garden gnomes. "Listen, those presents are just sitting there, unwrapped guilt from parents who missed soccer games." Outside, rain hammered the diner window. Inside, a waitress refilled their cups without making eye contact, having learned not to ask about the diagrams that involved trampolines and tactical glitter extraction. "So our plan is what, we dress as clowns?" Molly hated clowns. She had hated them since age eight when one had popped her favorite balloon and laughed. The irony was not lost on her. "Worse. You're the clown. I'm the incredibly handsome magician who distracts the moms." Bill leaned back, clearly proud of his genius. He had spent three hours watching YouTube tutorials on balloon dogs and now fancied himself a master of distraction and mild animal cruelty via latex. "Oh great, so I get the red nose and you get the cougars from book club?" She crumpled her napkin and threw it at him. It bounced off his forehead and landed in his water glass. Neither of them moved to retrieve it, watching it slowly dissolve into papier-mâché sadness. "Exactly. While I make balloon animals, you grab the gift table and run." The bell over the diner door jingled as a family with three children entered, each child clutching a brightly wrapped gift. Bill and Molly tracked the boxes with predatory focus, suddenly quiet and professional again, calculating weight and possible LEGO content. "Bill, there will be fifteen sugar-crazed kids and one very tired dad. This is a deathtrap." Bill shrugged and ordered more fries, using ketchup to draw what he claimed was an escape route but looked suspiciously like a frowny face with a party hat on top. "Relax, I've got the getaway van. It's got the words 'Free Candy' crossed out and 'Free Hugs' written over it." Molly stared at the ketchup blueprint for a long moment, contemplating whether she should cut her losses, fake her own death, and move to Canada where birthday parties involved less felony planning. "We're going to jail, not even cool jail." They left a tip, stole the family's gift on the way out, and called it small practice.
created_at
"2026-07-25T18:21:21.213Z"
7/25/2026, 6:21:21 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
27680
moderation_latency
(null)
generation_time
30304
tokens_prompt
75
tokens_completion
743
native_tokens_prompt
225
native_tokens_completion
5172
native_tokens_completion_images
0
native_tokens_reasoning
4514
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
0.02226225
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64fea1c54b89f455a04dc0"
is_byok
false
latency
559
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-1785003681-bcR0n1WUoRAvVKBrW44W"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003681-Ow8tyXxmOGBUYQCp0jE3"
upstream_id
"resp_6a64fea1c54b89f455a04dc0"
total_cost
0.02226225
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
66.22%
Dialogue to Total Word Ratio
Ratio: 32.87%, Deviation: 2.87%
neededClean
false
wordsTotal
505
wordsDialogue
166
83.1091%