NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4Q6PWN1A0HHAF7EKMRAY2
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
13.9s
Cost:
$0.008331
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3583%
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 abandoned bouncy castle rental shop smelled faintly of old pizza and rubber. Molly pressed her binoculars against the chain link fence behind the community center, watching a clown twist balloons. Bill spread a crudely drawn map on top of a cooler. The map was mostly crayon. "Okay, target is inside. Seven-year-olds, one piƱata, and at least twenty presents," Molly said. "Twenty presents? That's a better haul than the bank job," Bill said. "Focus. The moms have formed a perimeter around the juice boxes. That's perimeter one." Bill squinted at the window. A banner read HAPPY BIRTHDAY TIMMY in glitter that was already falling off. "So what's the plan? We go in through the front door with clown disguises?" "No. Clowns are expected to entertain. Do you know how to make a poodle out of a balloon?" "I know how to pop one. Does that count?" Molly sighed and tapped the map. In the center she had drawn a large pile of presents with dollar signs on them. "We go in through the side during cake time. That's when security is lowest. Everyone stares at the candles." "That's genius. My mom always cried during cake time. Very distracting," Bill said. "Right. So you will be in charge of crowd control. You keep the kids busy." "How?" "You juggle." "I can't juggle, Molly." "You juggled chainsaws last month." "Those were plastic toy chainsaws. I still dropped them." Molly lowered the binoculars and looked at him seriously. The bouncy castle behind them wheezed as it slowly deflated. "Bill, this is the score that gets us into early retirement. No more gas station ATMs. No more stealing garden gnomes." "But garden gnomes don't have parents who will chase you," Bill said. "Exactly. Lower risk, higher reward. Think of it. Unwrapped LEGO sets. Video games still in shrink wrap." Bill nodded slowly, getting inspired. "Okay, I'm in. So you grab the presents while I do my world famous juggling routine?" "Yes. Then we exfiltrate using the wagon in the parking lot." "The little red wagon?" "It's inconspicuous. Nobody suspects a little red wagon full of stolen birthday loot." Bill stared at the wagon. It had one squeaky wheel and a sticker that said HONK IF YOU LOVE MUFFINS. "What if Timmy sees us?" Bill asked. "We tell him we are the official birthday present inspectors. Very important job. Government mandated." "Do seven-year-olds understand government mandate?" "Timmy will. He looks like a smart kid." Through the fence they could hear the children singing happy birthday, off-key and extremely loud. The clown was now stuck inside a balloon. "That could be us," Molly whispered. "Stuck in a balloon?" Bill said. "No. Rich." She folded the map and shoved it into her pocket. "Remember, thirty seconds in, thirty seconds out. Nobody gets hurt and everyone gets cake," she said. "You think they'll share the cake even if we take the presents?" Bill asked. "Bill, this is a heist with morals. We take the presents, we leave the cake." "You're a good person, Molly."
created_at
"2026-07-25T17:21:13.956Z"
7/25/2026, 5:21:13 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8655
moderation_latency
(null)
generation_time
13760
tokens_prompt
75
tokens_completion
775
native_tokens_prompt
225
native_tokens_completion
1894
native_tokens_completion_images
0
native_tokens_reasoning
1184
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
0.00833075
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f08a4266ba1b69fa4f7e"
is_byok
false
latency
211
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-1785000073-fsuqjjA1TY9M4sYofOrk"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000073-1oBoF2NFRjAtJqjRTwNI"
upstream_id
"resp_6a64f08a4266ba1b69fa4f7e"
total_cost
0.00833075
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
98.71%
Matches word count
n/a
neededClean
false
words
506
0.00%
Dialogue to Total Word Ratio
Ratio: 64.19%, Deviation: 14.19%
neededClean
false
wordsTotal
511
wordsDialogue
328
49.3583%