NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K53ZE0YMPX67NW79J8RNBZ
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
33.9s
Cost:
$0.030477
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
99.9643%
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 blueprint of the community center across the sticky kitchen table, anchoring its corners with chipped mugs and a half-eaten toaster pastry. Red marker circled the service entrance, the hallway to the party room, and the mountain of brightly wrapped boxes stacked beside a banner that read Happy Birthday Timmy in glittery letters. Bill leaned over her shoulder wearing a striped shirt that already had balloon animal remnants stuck to it. "We are not robbing a children's birthday party." She stared at him with the flat disappointment usually reserved for parking tickets and his cooking. "We are liberating unappreciated plastic from ungrateful children." Molly tapped the blueprint hard enough to smudge the red ink. Outside, a minivan drove past with a dinosaur balloon bobbing against the rear window, squeaking faintly. "Bill, those presents are for a kid named Timmy who wants dinosaurs." Bill shrugged and produced a crumpled grocery list that he had repurposed as a heist plan, complete with juice boxes and tactical glitter. "Exactly, and dinosaurs are extinct, so he will not miss them." He pointed at the schematic with a chewed pen, leaving little teeth marks beside the air vent he claimed was their golden ticket. Molly imagined them wedged in that vent, surrounded by cobwebs and lost Legos. "The plan says we enter through the kitchen dressed as clowns." The kitchen door was supposedly unlocked during clown setup time, a twenty minute window where harried parents would accept any adult with face paint as hired entertainment. "I am not wearing clown shoes again, they squeak and betray us." Bill shuddered at the memory of their last circus-adjacent job, where his oversized shoes had squeaked through a silent museum and tipped off a guard dog who only wanted to play. "Fine, you can be the sad hobo clown, less honking, more brooding." Molly folded her arms, already picturing Bill in smudged makeup looking mournfully at a balloon poodle as if it owed him money. The plan was unraveling like cheap crepe paper. "What about the parents, the bouncy castle, and the security guard who is just a dad with a whistle?" Bill considered this formidable security force while stealing a carrot stick from Molly's open lunch bag, crunching loudly enough to emphasize his strategic thinking. "We distract them with cake, everyone stares at cake, even criminals with standards." Molly snatched the carrot back and checked the timeline again. The cake arrival was marked with three exclamation points and a frosting stain that looked suspiciously like a thumbprint. "And if Timmy cries?" The apartment fell quiet except for the humming refrigerator and the distant sound of children screaming joyfully at a playground, a sound Bill found deeply unsettling for professional reasons. "Then we give him the one present we keep, the educational one, nobody wants that anyway." She sighed with profound regret. "This is the worst heist we have ever planned, and we once stole garden gnomes." "Trust me, tomorrow Timmy gets trauma, we get toys."
created_at
"2026-09-03T08:10:44.549Z"
9/3/2026, 8:10:44 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2589
moderation_latency
(null)
generation_time
33911
tokens_prompt
75
tokens_completion
783
native_tokens_prompt
68
native_tokens_completion
7151
native_tokens_completion_images
0
native_tokens_reasoning
6478
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
0.03047675
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423044-HvC8D3pAdODou4nqNFbh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423044-cJ7NmFVp0laarpwddkuF"
upstream_id
"resp_6a992b855c5be11e7d0e494b"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992b855c5be11e7d0e494b"
is_byok
false
latency
518
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.03047675
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
99.93%
Dialogue to Total Word Ratio
Ratio: 29.88%, Deviation: 0.12%
neededClean
false
wordsTotal
502
wordsDialogue
150
99.9643%