NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4QGG39BXPAT9X6RK391GM
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
2m 10s
Cost:
$0.045968
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 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
The van smelled like old fries and bad decisions as Molly spread the birthday party floor plan across the dashboard. Bill studied it upside down while eating a juice box he had stolen for research purposes. Outside the suburban house, balloons bobbed in the heat and a banner screamed happy birthday Oliver in glittery doom. Molly whispered, "We are really doing this?" She adjusted the rearview mirror and watched a magician drop his rabbit cage on the driveway. Bill said, "Stealing from a six year old feels low, even for us." He slurped loudly, then crushed the empty box with criminal solemnity. Bill replied, "Relax, kid gets twenty presents, he will never miss three." Molly snorted and tapped the gift table on the map. Molly asked, "Three? You said all the presents yesterday." A minivan full of screaming children pulled up, and both thieves ducked as if dodging laser security. Bill grinned, "Change of plan, we take everything, donate half, keep Lego." Molly stared with weary affection earned through many terrible getaways. Molly said, "You just want the Lego Star Destroyer." Bill clutched his chest dramatically, spilling crumbs from his emergency party pretzels all over the stolen blueprints. Bill said, "Obviously, that thing retails for two hundred dollars." Across the street, parents unloaded coolers while a dad wrestled a dinosaur pinata. Molly crossed her arms, "Fine, but I am not wearing the clown suit." The infamous suit lay in the back, reeking of greasepaint and betrayal, its rainbow wig shedding like a nervous poodle. Bill pleaded, "You have to, parties love clowns, perfect cover." He held up the red nose with reverence, as though offering a diamond to a very skeptical queen. Molly groaned, "Last time I wore it, kids cried and dogs attacked." She still had teeth marks on her pride from the poodle incident at the twins baptism heist. Bill pointed triumphantly, "Exactly, tears equal distraction, dogs equal chaos, we win." Molly checked the timeline scribbled in crayon, marking cake o clock as the prime window for grand present larceny. Molly asked, "Okay genius, how do we carry twelve boxes quietly?" Bill produced a giant striped gift bag from behind the seat with the flourish of a discount magician. Bill said, "Big gift bag, big smile, walk out like tired parents." Molly imagined them waddling past the bouncy castle, sweating under frosting fumes, arms full of stolen robot dinosaurs. Molly raised an eyebrow, "And if someone asks for balloon animals?" Bill twisted an imaginary balloon with expert confidence, then mimed it popping and a child screaming with delight. Bill winked, "Tell them the clown only makes getaway cars." Molly laughed, picturing toddlers chasing them for twisty swords. Molly said, "You are the worst, you know that, right?" Bill bowed deeply, nearly toppling the bag of disguises. Bill said, "Worst thief, best brother, now pass the face paint." Molly tossed the kit and started the engine. Molly said, "Only if you share Lego." They rolled toward birthday infamy together.
created_at
"2026-09-03T08:03:56.042Z"
9/3/2026, 8:03:56 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5944
moderation_latency
(null)
generation_time
130149
tokens_prompt
75
tokens_completion
781
native_tokens_prompt
68
native_tokens_completion
10796
native_tokens_completion_images
0
native_tokens_reasoning
10095
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
0.045968
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422636-PzSnJSreuo1g84e6cQdf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422636-kewTZARGvgpKQeb0N9cu"
upstream_id
"resp_6a9929ec4993d1a5ecc54bf0"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a9929ec4993d1a5ecc54bf0"
is_byok
false
latency
722
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.045968
cache_discount
(null)
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: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%