NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5B08VXV3GXHNC6WE50AX9
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
35.7s
Cost:
$0.027583
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.9009%
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
The blueprints were spread across the sticky diner table between cold coffee and half-eaten pie. Molly traced a crayon-drawn map of the Johnson house with a chipped red nail. Outside, minivans blocked the street, all heading to the same jungle gym nightmare. Bill wore his stolen clown shoes. "Okay, listen. Seven kids, one bounce house, and a mountain of presents by the back fence." Molly whispered and tapped the map. Bill squeaked his shoes nervously. "This is our lowest point, Molly. We used to rob banks." "Yeah, banks with security guards and vaults. This has juice boxes and a piƱata." Bill leaned closer, frowning at the scribbled lasers which were clearly streamers. "How do we even get in? We are not six." "We are entertainers. You are Clowno the Unsettling. I brought face paint." "I hate kids, Molly. They stare into your soul." "Focus. The presents are left unattended during musical chairs. We go in through the side gate. You distract the parents with balloon animals." "I can only make a snake that looks like existential dread." "Perfect. The kids will love it. While you are doing that, I grab the wagon and roll." Bill stared at the loot list. It was written in glitter glue. "So we are stealing Robux gift cards and a Bluey plushie?" "And a Lego Death Star worth three hundred bucks. Do not underestimate the children's birthday economy." The waitress refilled their coffee. Molly folded the map into her jacket. The plan was insane even for them. Last month they had tried to steal a mascot costume and ended up in a parade. This time the stakes were lower but the humiliation higher. Outside the window a clown balloon escaped into the gray sky. Bill watched it rise and felt a deep kinship. Childhood was a scam, he thought, built on cake and lies. "What about the mom? She looks tough in the Facebook photos." "She is. She runs marathons and PTA. We avoid eye contact." "And the dad is grilling. He has tongs. He could weaponize tongs." "We have been through worse. Remember the petting zoo?" "Do not mention the petting zoo. That goat still haunts me." Molly stood and tossed cash on the table. Bill stood too, wobbling in clown shoes. "Last chance to back out, Bill. We could go straight." "We cannot afford straight. My clown car broke down again." "Then we steal from children. God help us." "God left when we put on these shoes." "Fine, but I get first pick of the good presents." He remembered the birthday parties he never had, the cheap apartments, the cakes from gas stations. Molly had promised him one big score would fix everything. It never did. But this job felt different, pettier, almost honest. The bell above the diner door rang and a child stared at his shoes laughing loudly. He did not laugh back. They pushed through the diner door, the little bell jingling, ready to commit their most shameless heist yet.
created_at
"2026-07-25T17:32:02.722Z"
7/25/2026, 5:32:02 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
32842
moderation_latency
(null)
generation_time
35532
tokens_prompt
75
tokens_completion
736
native_tokens_prompt
225
native_tokens_completion
6424
native_tokens_completion_images
0
native_tokens_reasoning
5751
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
0.02758325
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f3137fdfe855e6e04e05"
is_byok
false
latency
360
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-1785000722-zQ1HVeK7IX9rdFqKEKQs"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000722-QcDtLNKPk14dm1tuaH9t"
upstream_id
"resp_6a64f3137fdfe855e6e04e05"
total_cost
0.02758325
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
99.80%
Dialogue to Total Word Ratio
Ratio: 49.80%, Deviation: 0.20%
neededClean
false
wordsTotal
502
wordsDialogue
250
99.9009%