NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD61X6Q7EFSFSSENSC4XZ1N
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
41.4s
Cost:
$0.031795
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.44%
Dialogue to Total Word Ratio
(details)
99.7219%
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 spread the blueprint across the hood of the getaway van, which was actually just her mom's dented minivan with a half-eaten granola bar fused to the dashboard. "Okay, Bill, Johnson house. Bouncy castle here, present mountain here, right by the back fence where the dog has clearly given up." Bill squinted at it, tugging his fake mustache that kept falling into his coffee. "That is not a blueprint. That is a crayon drawing you stole off Timmy's fridge." "It is advanced recon. Timmy invited fifteen kids. That's fifteen gift bags of pure, sticky-fingered profit." The wind flipped the paper and revealed a juice box stain shaped suspiciously like Texas. "On a scale of Robin Hood to supervillain, how evil is stealing from a six-year-old, Molly?" "We are not evil. We are redistributing wealth from children who cannot appreciate Lego to adults who can sell Lego." Bill sighed and looked at the house where a dad in cargo shorts was already sweating over a grill. "So we just walk in like normal creepy adults?" "No. We are entertainers. You are Mr. Giggles, I am Mrs. Giggles. Twins. Separated at clown school." "I hate clowns. And I hate that you made me Google how to twist a balloon dog." "Last time you twisted balloons you popped twelve and made one toddler cry. Perfect distraction." Molly zipped open a duffel bag full of red noses, oversized shoes, and what was definitely a stolen traffic cone. "Plan: we go during pin-the-tail. Dad is distracted, mom films everything vertically, kids scream at donkey." "And the present table? It's alarmed? Guarded by a bouncy castle dragon?" "Worse. Grandma. She sits there. She has seen war, taxes, and Peppa Pig. Nothing scares her." Bill laughed despite himself, then immediately felt guilty for imagining tackling a grandmother for a Nintendo Switch. "I will trap her with conversation about her grandson being gifted. You grab bag, run to compost bin." "What if we only get socks with dinosaurs? Or, worse, educational books?" "Then you finally learn to read. Win-win. Look, fifteen presents minimum. One could be a bike." Molly folded the map with the seriousness of a general, which mostly meant it ripped halfway. "Trust me. We walk out with Bluey backpacks and nobody suspects the clowns because clowns are already suspicious." "If we get caught stealing from kids, our mugshots will be on the neighborhood Facebook group forever." "Then we will be legends. Sad, banned-from-birthdays legends. Are you in?" "Fine, but if we get a Paw Patrol cake, I get the corner with extra frosting." Bill pulled on the red wig, which immediately made him look like a depressed carrot. Molly honked a horn for morale. "We are going to be the worst best clowns these kids have ever seen. Let's go steal childhood joy." "And if Timmy cries, we tell him capitalism is the real thief. That should calm him." "Molly, you are a terrible influence and an even worse clown." "Thank you, let's go now."
created_at
"2026-07-25T17:44:33.246Z"
7/25/2026, 5:44:33 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
38424
moderation_latency
(null)
generation_time
41152
tokens_prompt
75
tokens_completion
758
native_tokens_prompt
225
native_tokens_completion
7415
native_tokens_completion_images
0
native_tokens_reasoning
6725
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
0.031795
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f6015c07a9bbb1af4f6a"
is_byok
false
latency
244
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-1785001473-sAuJlmeIuMJGLZ8QYGPj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001473-Dt1BWfSD8vcyqtvTLGsT"
upstream_id
"resp_6a64f6015c07a9bbb1af4f6a"
total_cost
0.031795
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
99.44%
Dialogue to Total Word Ratio
Ratio: 70.33%, Deviation: 0.33%
neededClean
false
wordsTotal
509
wordsDialogue
358
99.7219%