NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5WJE0GTJQKY2ZR4YV2GMC
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
27.7s
Cost:
$0.022669
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
Molly spread the blueprint across the stolen ice cream truck's dashboard and weighted the corners down with stale cupcakes. Bill squinted at the crayon-drawn diagram, which featured laser tripwires labeled as juice boxes and a guard dog labeled as Timmy's mom. "Okay, so Timmy's mom is the main obstacle." Molly said, tapping a frosting stain marked X. "She's terrifying. Last time she made me eat carrot sticks and apologize to a clown." Bill whispered, adjusting his stolen clown nose which kept squeaking. The target was a suburban backyard birthday party with an estimated haul of twenty plastic-wrapped presents piled beside a bouncy castle. "Twenty presents, Bill. That's twenty untouched action figures, and according to my intel, one limited edition dinosaur that roars." she hissed. "We are two grown adults plotting to steal toys from a six-year-old named Timmy. Have we hit rock bottom?" Bill asked, but his eyes gleamed at the thought of the dinosaur. "Rock bottom is paying rent, Bill. This dinosaur pays rent for a year. Focus." She pointed to the blueprint's entrance route through the side gate disguised as entertainers. "We go in as the magicians. You distract the kids, I grab the loot." "I can't do magic. The last time I tried I made a rabbit file for unemployment." Bill protested, his oversized shoes flopping as he paced inside the cramped truck. "You don't need magic, just pull a quarter from Timmy's ear while I grab the presents." She held up a sack labeled TOTALLY NOT STOLEN LAUNDRY. "What about the bouncy castle? My back hasn't bounced since ninety-eight." He rubbed his spine and eyed the sketch of the inflated deathtrap with suspicion. "You vault over it. Or bounce over it. Just don't pop it, or every kid will scream and Timmy's mom will deploy." Molly traced the escape route leading past the sprinkler system and over the fence behind the cake table. "There's cake? What kind of cake?" "Chocolate with sprinkles, but we are not eating the evidence, Bill." She narrowed her eyes as Bill visibly drooled behind his red nose. "One slice won't hurt. For morale. Thieves need morale and sugar." He attempted a sad clown face which only made him look constipated. "Fine, one slice after we secure the bag. Then we vanish before Happy Birthday ends." She folded the blueprint and shoved it into her striped burglar shirt which clashed terribly with her party hat. "Do I have to wear this wig? It itches and I think it has glitter lice." He tugged at the rainbow afro perched crookedly on his sweating head. "Yes, you do. Timmy requested a scary clown, and you are perfectly scary without trying." Bill sighed and honked his nose, which squeaked loudly enough to startle a pigeon outside. "Let's steal those presents before I lose my nerve and my lunch." "That's the spirit. Operation Birthday Snatch is a go now." They bumped fists, the truck door creaked open, and distant children singing off-key filled the summer air.
created_at
"2026-09-03T08:24:10.438Z"
9/3/2026, 8:24:10 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3985
moderation_latency
(null)
generation_time
27626
tokens_prompt
75
tokens_completion
883
native_tokens_prompt
68
native_tokens_completion
5314
native_tokens_completion_images
0
native_tokens_reasoning
4496
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
0.0226695
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423850-IKlglipfY7cvOB83QnPI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423850-c2Cbhm8uLDqOpnXBiGIm"
upstream_id
"resp_6a992eaaf72352cecbcd4607"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992eaaf72352cecbcd4607"
is_byok
false
latency
370
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.0226695
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: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
506
wordsDialogue
253
100.0000%