NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4QEZ3VWHF8HBCZW5DJFH5
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
1m 29s
Cost:
$0.032788
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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 van smelled like old fries and bleach while Molly studied the bright flyer taped crookedly above the steering wheel with intense focus this morning. "Okay Bill, the target is a seven year old birthday party with a clown, a pony, and supposedly a mountain of wrapped presents inside today." Bill squinted through the windshield at the suburban house with balloons bobbing wildly and sighed like a man facing dental surgery without anesthesia this afternoon. "Molly, I have robbed banks, casinos, and one aquarium, but stealing from children feels low, even for us seasoned professional criminals and I feel guilty" Molly snorted and unfolded a crayon drawn map showing the backyard, the kitchen window, and a large X marking the glowing present table in red. "Guilt does not pay rent Bill, and those kids get mountains of toys they forget by Tuesday while we struggle to eat every single day" Bill drummed his fingers nervously on the dashboard as screaming children chased each other around a bouncy castle shaped like a dragon in the heat. "Fine, what is the brilliant plan, dress as clowns, sneak past parents, grab everything, and sprint for our lives screaming through sprinklers and cake crumbs" Molly grinned widely and pulled two squeaky clown wigs, red noses, and oversized polka dot costumes from a stained duffel bag behind the front seats. "Exactly, we walk in during the magic show, pretend we are backup clowns, and load gifts into the fake birthday cake cart quietly without panic" Bill pulled the itchy rainbow wig over his balding head and stared miserably at himself in the cracked rearview mirror above the steering wheel today. "I look ridiculous Molly, the kids will scream, the parents will call police, and the real clown will expose us instantly without any mercy today" Molly honked his red nose loudly and laughed until tears streamed down her powdered white face in the hot van while children sang outside nearby. "Relax big guy, no one questions clowns, they just assume we smell funny, act weird, and belong near screaming toddlers eating frosting with bare hands" Bill practiced his wobbly clown walk across the cracked parking lot while juggling three stolen oranges to impress nobody watching from behind the tall fence. "What if the presents are all socks, educational books, and kale chips from health obsessed parents trying to ruin childhood for sweet innocent little kids" Molly pointed toward the glittering pile visible through the fence where boxes wrapped in dinosaurs and rainbows towered triumphantly above the screaming happy birthday crowd. "Look at that glorious haul Bill, action figures, game consoles, bikes, and probably a pony wrapped with a giant bow waiting just for clever us" Bill sighed deeply, squeezed into oversized floppy shoes, grabbed the hollow cake cart, and nodded with reluctant criminal resolve today as balloons popped loudly nearby. "Let us steal those presents fast before my dignity, my back, and my last shred of sanity completely collapse under this stupid rainbow wig today"
created_at
"2026-09-03T08:03:54.474Z"
9/3/2026, 8:03:54 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7196
moderation_latency
(null)
generation_time
88365
tokens_prompt
75
tokens_completion
784
native_tokens_prompt
68
native_tokens_completion
7704
native_tokens_completion_images
0
native_tokens_reasoning
7062
native_tokens_cached
35
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
0.0327885
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422634-3Pk77fZS4iWrIC8sMtwz"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422634-FgoiNYviknSsurlu2FA2"
upstream_id
"resp_6a9929ee36a974b790384ec9"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a9929ee36a974b790384ec9"
is_byok
false
latency
3994
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.0327885
cache_discount
0.0000385
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
250
100.0000%