NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4YNQHNRH5W8ST82PN5BFB
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
1m 17s
Cost:
$0.045165
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 70% 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 community center on Maple Street buzzed with bright balloons and screaming kids while Molly and Bill watched from the dented van across the road. "Look at that haul," Molly whispered, pressing her face to the windshield. "That pirate cake table is stacked with presents." "Those are for six year olds," Bill muttered, adjusting his fake mustache. "We are professional thieves, not birthday monsters." "Exactly," Molly said. "Six year olds cannot chase us. They get tired after juice boxes and fall asleep during cartoons." "That is cold," Bill said. "Even for you. Last week you cried at a dog food commercial." The van smelled like old fries and Bill shifted the laundry bag full of tools onto his lap. "Okay, listen," Molly said. "The party starts at three. Parents drop gifts on the side table and go gossip by the punch." "So we walk in dressed as clowns?" Bill asked. "I hate clowns. They know things." "No clowns," Molly said. "We go as tired parents. Nobody questions tired parents. We bring a stroller and empty diaper bag." Bill stared at the glittery banner that read Happy Birthday Leo and sighed deeply. "Leo is turning seven," Bill said. "What if Leo cries? I cannot handle crying. I will confess everything." "Nobody will cry," Molly said. "We wait for the magician. When he pulls the rabbit, we pull the presents." "That is actually smart," Bill said. "Distraction plus chaos. But how do we carry twenty screaming toys without squeaking?" "Diaper bag," Molly said. "Plus stroller bottom. Plus my giant purse. Babies need lots of gear. Nobody checks." "What about the bouncy castle guard?" Bill asked. "That teenager looks serious. He has a whistle." "We bribe him," Molly said. "Kids love bribes. We offer extra cake and unlimited castle time." "And the moms?" Bill asked. "Moms see everything. My mom still knows about the hamster incident." "Compliment them," Molly said. "Tell every mom she looks rested. Rested moms get confused and happy." Across the street a clown twisted balloon swords while parents unloaded shiny wrapped boxes onto a long table. "Oh wow," Bill said. "That blue one is huge. Probably a scooter. Do kids even appreciate scooters?" "Focus," Molly said. "We grab, we bag, we stroll out calmly. No running, no masks, no villain laugh." "No villain laugh?" Bill asked. "You always take the fun parts away. What about code names?" "Fine," Molly said. "You are Sleepy Dad. I am Coffee Mom. The baby is our lookout." "We do not have a baby," Bill said. "Do we steal a baby too? That feels like extra paperwork." "No," Molly said. "We borrow a doll. Put sunglasses on it. Nobody looks closely at sleeping babies." Bill grinned and started the van as music drifted over and kids screamed for cake. "Let's steal some birthday joy," Molly said. "For charity. Our charity." Bill laughed loudly. "Deal," Bill said happily. "But if anyone sings I am joining in before we run away fast with the presents today."
created_at
"2026-09-03T08:07:50.777Z"
9/3/2026, 8:07:50 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3495
moderation_latency
(null)
generation_time
77395
tokens_prompt
75
tokens_completion
772
native_tokens_prompt
68
native_tokens_completion
10607
native_tokens_completion_images
0
native_tokens_reasoning
9892
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
0.04516475
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422870-3cGCDyedm4Ka7iFPiveK"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422870-C4hFpLnCKArAHz9t9vD0"
upstream_id
"resp_6a992ad6761d5e7b19694212"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992ad6761d5e7b19694212"
is_byok
false
latency
694
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.04516475
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: 70.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
350
100.0000%