NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5GG8N9H0KKKQ9588G21V1
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
29.8s
Cost:
$0.029070
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
The warehouse behind the community center smelled faintly of cardboard, cold pizza, and industrial cleaner. Molly spread the hand-drawn blueprint across an overturned milk crate, smoothing glitter and juice-box stains with careful fingers. Bill hovered nearby, his oversized clown shoes squeaking against concrete, trying not to step on the plan. "Molly, we are seriously going to steal birthday presents from six-year-olds?" "Relax, Bill. Those twins have more plastic junk than a toy factory. We're redistributing wealth." "Redistributing? We're stuffing LEGOs into a duffel bag. And trying not to get tackled by angry moms. That's the redistributing part. Trust me. Please." She pointed to a side entrance marked with a smiley face, the kitchen door propped open for catering trays. A teenage magician was scheduled to perform, providing perfect cover for two additional entertainers. Bill fiddled with his rainbow wig, which itched terribly and smelled faintly of hairspray and regret badly. "So I waddle in wearing these shoes and yell surprise?" "No, you waddle in, do the balloon animal thing, and keep the parents busy while I grab the pile." "What if they ask me to make a giraffe? I can only make worms." "Then make worms and call them art." Molly rolled her eyes and produced two crumpled jumpsuits covered in bright patches and squeaky buttons. The plan hinged on confidence and the fact that no parent questions a clown at a children's party. Outside, the bouncy castle wheezed as kids screamed happily, oblivious to the impending present heist today. "Okay, but the gift table is right next to the mom with the laser eyes." "Mrs. Henderson? She's just protective." "Protective? She once chased a piƱata thief three blocks. On foot. In heels." "Perfect, she'll be watching the magician. We go straight for the mountain of wrapped boxes quickly now." Bill tightened his red nose until it squeaked, staring at the blueprint's final detail, an escape route through the ball pit. Molly had drawn arrows leading to the parking lot where their van waited, engine running. It was absurd, risky, and thrilling, like every good idea they'd ever had together. "What do we do if a kid starts crying because we took his dinosaur?" "We tell him sharing is caring and vanish." "That's cold, Molly. Even for us." "Fine, leave one present. The socks. No kid cries over socks." "Deal. But I get to keep the castle if it fits." A cheer erupted from the community center as the magician botched a trick and kids howled with laughter. Molly folded the blueprint, shoved it into Bill's oversized pocket, and grinned. Whatever happened next would be chaotic, colorful, and absolutely unforgettable, just the way they liked their jobs very much indeed. "Ready to become the worst children's entertainers in history?" "Ready as I'll ever be. Let's steal some joy. I mean, presents." "Steal presents, borrow joy, same difference. On three we shuffle like penguins. One, two, three, waddle!" "Waddle!" "If we get caught, we were never here and you saw glitter."
created_at
"2026-09-03T08:17:35.004Z"
9/3/2026, 8:17:35 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2419
moderation_latency
(null)
generation_time
29789
tokens_prompt
75
tokens_completion
779
native_tokens_prompt
68
native_tokens_completion
6820
native_tokens_completion_images
0
native_tokens_reasoning
6106
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
0.02907
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423455-5YLKTUnQDIrFI1IYUdE1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423455-3XXa41gSgmN1oTYLwm1m"
upstream_id
"resp_6a992d1f3ceae4c3346f42e8"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992d1f3ceae4c3346f42e8"
is_byok
false
latency
1162
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.02907
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
504
wordsDialogue
252
100.0000%