NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5GE1QKD68JEB5892Q9228
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
32.7s
Cost:
$0.030800
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.8929%
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 fryer oil and bad decisions. Molly taped the blueprint of the Sunny Smiles Community Center to the steering wheel while Bill wrestled with a tangled rainbow clown wig. Outside, mothers unloaded juice boxes and fathers assembled a lopsided bounce house while a plastic banner thumped against the brick wall in the wind. "This is humiliating," Bill said. "You wanted to look professional," Molly said. "I meant Ocean's Eleven, not Bozo," Bill said. Molly pointed to a hand drawn square labeled BOUNCE HOUSE. "The presents are piled by the stage. Twenty kids, one clown and a mountain of wrapping paper." She had drawn the escape route in glitter pen, which seemed overly festive for grand larceny. "So we walk in dressed as clowns and just take them?" Bill asked. "We walk in as clowns and do the party," Molly said. "We do balloon animals until the sugar crash hits. Then we load gifts into the laundry bag." "What if they notice we are stealing birthday presents from children?" Bill asked. "They will not notice because we are hilarious," Molly said. "Also you will cry inside that tiny car." Bill held up the wig. "Do I have to wear this?" "Yes, the ad said two clowns, Sparkles and Jingles," Molly said. "You are Jingles." "I hate Jingles," Bill said. "You hated stealing copper pipes too and you did that," Molly said. Bill sighed and pulled the wig on sideways. The van door squeaked open and a gust of outside air sent napkins flying. Across the lot, children shrieked inside the bounce house and somewhere a tired speaker crackled out a cheerful birthday song on endless loop. "Okay, what is the getaway plan?" Bill asked. "We push the gift bag out the exit by the ball pit," Molly said. "I propped it open with a juice box." "That is genius or the saddest crime ever," Bill said. "It can be both," Molly said. "Remember, no one suspects clowns. We honk, we juggle, we vanish." "Do you even know how to juggle?" Bill asked. "No, but I can drop things convincingly," Molly said. "You just keep the kids away from the table." Bill stared at the blueprint, then at the baggy polka dot suit. The suit smelled faintly of popcorn and previous failures, and the oversized shoes squeaked whenever he shifted his weight nervously. "What if the birthday boy starts crying?" "Then you make him a balloon dog and mention capitalism," Molly said. "Right," Bill said. "And what do we do with twenty identical plastic dinosaurs?" "We sell them and finally fix the van's brakes," Molly said. Bill zipped the clown suit and squeaked his red nose. It honked limply. Molly adjusted her red nose, checked the oversized laundry bag folded in the back seat, and winked with the confidence of someone who had never been caught sober in bright daylight. "Let us go steal some joy," Molly said. "We are terrible people," Bill said. "The worst, now smile bigger," Molly said.
created_at
"2026-09-03T08:17:32.733Z"
9/3/2026, 8:17:32 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2991
moderation_latency
(null)
generation_time
32647
tokens_prompt
75
tokens_completion
756
native_tokens_prompt
68
native_tokens_completion
7227
native_tokens_completion_images
0
native_tokens_reasoning
6537
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
0.03079975
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423452-LvPSselifaguaUOtSjPE"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423452-YPO24acTUoROtz1ALRIK"
upstream_id
"resp_6a992d1d6c07e327d5454547"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992d1d6c07e327d5454547"
is_byok
false
latency
995
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.03079975
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
99.98%
Matches word count
n/a
neededClean
false
words
502
99.80%
Dialogue to Total Word Ratio
Ratio: 49.80%, Deviation: 0.20%
neededClean
false
wordsTotal
502
wordsDialogue
250
99.8929%