NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD563N6F4BNH902GNDD5QM1
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
12.5s
Cost:
$0.006699
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 the length of the van, stepping over empty coffee cups, while Bill sat on an overturned bucket studying a hand-drawn map of Maple Street. "This is the dumbest job we've ever considered," Molly said. "It's a children's party, Molly. Low security, high reward. Those kids get spoiled rotten." "You want to steal from a six-year-old? You know whose birthday it is, right? It's your niece's." "Second cousin twice removed, and that distinction matters legally and morally," Bill said. "Besides, have you seen what kids get these days? Tablets, bikes. One kid got a tiny electric car last year. A car!" "And how exactly do you plan to walk out of a backyard full of parents holding twenty wrapped boxes without anyone noticing?" "We use distraction. Classic misdirection. I dressed as a clown before, remember?" "Oh, I remember," Molly said. "You cried when the balloon poodle popped and the kids had to comfort you." "They were very supportive children. Look, we just mingle. We act like we belong. Nobody questions a guy with a plate of cake." "Bill, they hired an actual magician. Two entertainers is suspicious." "Then you're the magician's assistant. You wear the sparkly outfit." "I am not wearing sequins to commit a felony against children," Molly said. "It's not a felony, it's a... it's a bold repossession of plastic. Think of the resale value." "The resale value of a talking dinosaur that sings the ABCs? Be serious." "The dinosaur alone is eighty bucks new in box. And there's Legos. Parents always buy Legos." "Okay, mastermind," Molly said. "Walk me through the exit strategy. We have a wagon full of Paw Patrol gift bags. Then what?" "Then we walk briskly away, like we have somewhere very important to be, which we do, because we have stolen goods." "You rehearsed that in the mirror, didn't you?" "Twice," Bill said. "The brisk walk is key. Confidence is ninety percent of theft." "And the other ten percent?" "Not getting caught by my sister. She will literally kill us if she finds out we ruined Chloe's party." "Chloe is turning six, Bill. She asked for you to come. She drew you a picture." "She drew me as a potato with arms. I'm emotionally wounded." "So your revenge is to steal her friends' birthday presents and make her cry?" "When you say it like that it sounds bad," Bill said. "Because it is bad. That's the definition of bad." "Fine, what if we just take one present? The big one? The one that looks like a bike box?" "That's even worse. Then one kid gets nothing and Chloe gets blamed for losing it." Bill stared at his map, then folded it up very slowly. "Okay, okay, you have a point," Bill said. "This plan has flaws." "A few." "So we pivot. We go to the party, we eat cake, we act normal, and we don't steal anything." "That's called attending a party, Bill. That's not a pivot, that's how normal people live." "But we still wear disguises?" "No." "Can I still do the brisk walk to the snack table?" "Yes," Molly said. "You can briskly walk all you want. Just bring me cake while you're at it."
created_at
"2026-07-25T17:29:22.359Z"
7/25/2026, 5:29:22 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6493
moderation_latency
(null)
generation_time
12423
tokens_prompt
75
tokens_completion
787
native_tokens_prompt
225
native_tokens_completion
1510
native_tokens_completion_images
0
native_tokens_reasoning
778
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
0.00669875
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f272535593a3037f4c27"
is_byok
false
latency
358
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-1785000562-E7n0Wh3DqgDQ7g96jIgS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000562-Esg8DSaCRF6beNCGr12y"
upstream_id
"resp_6a64f272535593a3037f4c27"
total_cost
0.00669875
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
0.00%
Matches word count
n/a
neededClean
false
words
535
0.00%
Dialogue to Total Word Ratio
Ratio: 89.59%, Deviation: 19.59%
neededClean
false
wordsTotal
538
wordsDialogue
482
0.0000%