NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5MXAD80WGGW31FVZT7TK2
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
11.8s
Cost:
$0.006673
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0014%
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 crumpled flyer across the dashboard of the getaway van. It read TIMMY'S 7TH BIRTHDAY BLOWOUT! in glitter glue that was already flaking onto the upholstery. The flyer had been taped to a lamppost next to a bouncy castle rental coupon. "This is rock bottom," Bill said from the driver's seat, eating a juice box he had found somewhere. Molly tapped the flyer with a chipped red nail. According to her, this was a target-rich environment. "Tell me again why we're robbing a seven-year-old?" Bill asked. "We're not robbing the kid, we're liberating poorly secured assets from a high-yield domestic location," Molly said. "That's literally robbing a seven-year-old, Molly," Bill said. Molly ignored him. She had drawn a floor plan on the back of a pizza receipt. It showed the Johnsons' backyard, the side gate, and what appeared to be a very angry goose. "The intel says presents are on the picnic table, left side, unguarded during cake time," she whispered, even though they were alone in a parked van. Bill stared at the goose drawing. "What is that?" "That's Kevin. The neighbor's goose. He's neutral. We can bribe him with breadcrumbs." "You want to bribe a goose to steal LEGO sets?" "Bill, we need rent money and your dog ate my lucky crowbar. We are pivoting to the youth market." Bill slurped his juice box loudly. The plan, as far as he understood it, was to walk in wearing clown pants she had bought at the thrift store. "So we just walk in?" he asked. "We blend in," Molly said. "Everybody loves a clown. Or two clowns who are very sweaty and late." "And then we just grab the pile and run?" "And then we execute a tactical present extraction during the distraction window when the magician does the rabbit trick," Molly said. Bill considered this. He considered the ethics. He considered that the last time they tried a sophisticated job they got locked in a self-storage unit for six hours. "Isn't there gonna be like, twenty parents there filming everything?" he said. "Which is why we need speed, subtlety, and this fake mustache I found," Molly said, holding up what was clearly a caterpillar. Bill sighed and put his juice box down. "Molly, what if we get chased by kids hopped up on cake? Those kids are fast." Molly folded the flyer with the reverence of a general folding a battle map. "Listen, nobody wants to steal from a kid's birthday party," she said. "But that present pile is taller than you and half of it is probably not even opened yet. Think of the resale value." "I am thinking about it, and I feel bad about it," Bill said. "Good. Guilt means you have morals. Morals mean you won't mouse-trap the Star Wars LEGO," she said. From down the street they could hear a faint, off-key chorus of Happy Birthday and the deflating wheeze of a bouncy castle losing air. Molly pulled the clown pants out from the back seat. They smelled faintly of old popcorn. "Let's go steal some joy," she said. "Let's really not phrase it like that," Bill said, getting out of the van.
created_at
"2026-07-25T17:37:27.386Z"
7/25/2026, 5:37:27 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6274
moderation_latency
(null)
generation_time
11403
tokens_prompt
75
tokens_completion
773
native_tokens_prompt
225
native_tokens_completion
1504
native_tokens_completion_images
0
native_tokens_reasoning
771
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
0.00667325
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f4578fe2c37ac1bb4cd7"
is_byok
false
latency
328
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-1785001047-p8elWEE6lNz1MZzm8Y06"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001047-i7yTB4GitRxuwx1gvu3H"
upstream_id
"resp_6a64f4578fe2c37ac1bb4cd7"
total_cost
0.00667325
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
532
0.00%
Dialogue to Total Word Ratio
Ratio: 50.28%, Deviation: 20.28%
neededClean
false
wordsTotal
541
wordsDialogue
272
0.0014%