NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4ZKAT7BAV837NA2KC5P0J
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
21.0s
Cost:
$0.015904
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.98%
Dialogue to Total Word Ratio
(details)
99.9905%
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 blueprints across the hood of their dented van. The paper showed not a bank vault but a bouncy castle, a buffet table, and a towering pile of brightly wrapped boxes marked with a big red X. Bill stared, his trench coat flaring in the wind. "So this is the big score, he asked. We are hitting Timmy Johnson's seventh birthday." Molly tapped the X with a chipped purple fingernail. "That's thirty presents. Thirty. The Johnsons always overcompensate. Last year they gave every kid an iPad. Imagine what's in there this year." Bill frowned so hard his fake moustache slipped. "I became a thief for the thrill. For diamonds. For safecracking. Not for stealing a Lego set from a child named Timmy." Molly rolled her eyes and pulled a squeaky red nose from her pocket. "You got caught trying to steal copper wire last week. You need to lower your standards." She stretched the elastic and snapped it onto his face. "I have standards, Molly. What kind of monsters steal from kids? What next, we rob a lemonade stand?" Molly ignored him and pointed at two circles on the blueprint. "We are not monsters. We are opportunists. Listen. The plan is simple. I go in as the clown. You go in as my depressed donkey assistant." Bill looked deeply offended on behalf of donkeys everywhere. "Why am I always the donkey?" He asked. "Because you have the natural charisma of a donkey. You will carry the big striped bag for used balloons. Except we fill it with presents." The plan, despite its absurd costume requirements, was actually solid. The backyard gate would be open for the catering van. Molly had timed the magician's set to last exactly twelve minutes, during which every parent would be forced to watch a man pull a rabbit from a hat while pretending to be impressed. That was their window. Bill would waddle in, looking mournful, and start collecting discarded wrapping paper into the striped bag, then subtly transition to collecting un-discarded presents. Meanwhile Molly would twist balloons into elaborate animals so complicated that they would distract the children through sheer confusion. She had practiced making a giraffe that looked more like a tax attorney. Nobody questioned a clown. Nobody ever truly saw a clown. They were invisible, hiding behind greasepaint and desperate cheer. Bill sighed and adjusted the donkey ears Molly handed him. They were itchy and one ear flopped permanently downwards, giving him an air of profound existential sadness that, admittedly, suited the role perfectly. Molly checked her reflection in the van window, smearing blue eyeshadow up to her eyebrows. Somewhere down the street, a chorus of seven year olds sang happy birthday off key. The pile of presents was waiting. The heist of the century, or at least the afternoon, was about to begin. Neither thief felt good about it, but the promise of thirty free juice boxes sealed the deal. They marched toward destiny, greasepaint gleaming. Into suburban infamy together.
created_at
"2026-07-25T17:25:49.026Z"
7/25/2026, 5:25:49 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18189
moderation_latency
(null)
generation_time
20897
tokens_prompt
75
tokens_completion
753
native_tokens_prompt
225
native_tokens_completion
3676
native_tokens_completion_images
0
native_tokens_reasoning
3016
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
0.01590425
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f19d00af9f0293374092"
is_byok
false
latency
408
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-1785000349-hbe47dw849hriUk79eXP"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000349-BfVQv836wvv8997KQyoY"
upstream_id
"resp_6a64f19d00af9f0293374092"
total_cost
0.01590425
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
501
99.98%
Dialogue to Total Word Ratio
Ratio: 29.94%, Deviation: 0.06%
neededClean
false
wordsTotal
501
wordsDialogue
150
99.9905%