NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD58902R2JG9CMDHWT9VWK8
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
10.4s
Cost:
$0.006163
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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
Molly spread the flyer for Timmy's 7th Birthday Extravaganza across the hood of the getaway van. The cartoon dinosaur on it wore a party hat and looked deeply judgmental. "Okay, walk me through it again," Bill said, squinting at the laser-printed map of the Johnsons' backyard. "We go in through the side gate at precisely fourteen hundred hours," Molly said. "You mean two in the afternoon when the magician shows up?" "I mean fourteen hundred hours, Bill. We need to sound professional. This is a high stakes operation." Bill tapped the flyer. "It says there will be juice boxes and a bouncy castle. Are we the bad guys here?" "We are career criminals, Bill. We have standards. Low standards, but standards." "Yeah, but stealing from a seven-year-old seems like a new low, even for us," Bill said. "It's not just one seven-year-old. It's twenty seven-year-olds' worth of presents piled on one table. It's an economy of scale," Molly said. "Right, right. So what's the haul?" Molly flipped open her notebook. "According to my surveillance, we are looking at three LEGO sets, two remote control trucks, and what appears to be a very large stuffed giraffe." "I love giraffes," Bill whispered. "Focus. The targets will be distracted by the piñata. That's our window. While little Timmy is being violently swung at a papier-mâché donkey, we move." "And the parents?" "Also watching Timmy hit the donkey. Adults love watching children commit donkey violence," Molly said. Bill nodded slowly. "Okay, so I go in dressed as the clown. You create a diversion." "Wait, why am I the diversion? You said I could be the clown," Molly said. "Because you are terrible at being a clown. You did that birthday last month and made three kids cry." "I made them cry because they need to understand that life is unpredictable and often disappointing," Molly said. "See? That's why I'm the clown." Molly sighed and folded the flyer. "Fine. You're Coco the Clown. I'm the responsible adult who is there to pick up her nephew." "Do you have a nephew?" "I will acquire one for verisimilitude," Molly said. Bill pulled a red nose from his pocket and put it on. It squeaked. "How do I look?" "Like a man who is about to steal a stuffed giraffe from a child and feel conflicted about it," Molly said. "I'm not conflicted. I'm committed. What's our exit strategy?" "We walk out calmly with a wagon full of presents, because no adult at a children's party wants to confront a weird clown and his intense sister," Molly said. "I'm not your brother." "Cover identities, Bill. Keep up. If anyone asks, your name is Coco and you have crippling student loan debt from clown college." "I do have that," Bill said sadly. Molly patted his oversized shoe. "Then the performance will be authentic. Now, are you ready to become the most hated man at an elementary school?" Bill stood up straight, his rainbow wig catching the wind. "Let's go steal some joy."
created_at
"2026-07-25T17:30:33.355Z"
7/25/2026, 5:30:33 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5350
moderation_latency
(null)
generation_time
10308
tokens_prompt
75
tokens_completion
755
native_tokens_prompt
225
native_tokens_completion
1384
native_tokens_completion_images
0
native_tokens_reasoning
688
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
0.00616325
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f2b99e7e64eb60484fa5"
is_byok
false
latency
136
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-1785000633-oTXdh3qLhUJPpuNxv80t"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000633-peodDDwjyDgZhYQNzhSN"
upstream_id
"resp_6a64f2b99e7e64eb60484fa5"
total_cost
0.00616325
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
99.92%
Matches word count
n/a
neededClean
false
words
503
0.00%
Dialogue to Total Word Ratio
Ratio: 78.67%, Deviation: 28.67%
neededClean
false
wordsTotal
511
wordsDialogue
402
49.9595%