NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5EKQHYMKW2WEWAPFWH7RE
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
27.2s
Cost:
$0.020639
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
96.97%
Dialogue to Total Word Ratio
(details)
78.6245%
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 getaway van smelled faintly of bologna sandwiches and desperation. "Okay, walk me through it again. We are stealing from a six-year-old?" Bill unfolded the crumpled invitation he had lifted from the recycling bin. "Technically we are stealing from twelve six-year-olds. It's Timmy's birthday. His mom went absolutely overboard. There's a mountain of presents." Molly stared at the glitter-covered invitation like it might explode. "Bill, we used to rob banks. Actual banks. With vaults and guards and dignity." "And what did that get us? The van still smells like bologna. The kid's got a PS5, two scooters, and what I think is a genuine Lego Death Star. No guards." He tapped the hand-drawn map showing the bounce house and the juice box station. "There are literally going to be clowns. And parents. Judgy suburban parents." "Perfect cover. You distract the clown, I grab the loot. Operation Pinata Smash is foolproof." Molly leaned over the steering wheel, groaning. "Last time you said foolproof we got stuck in a petting zoo overnight. I still have goat trauma." "That goat was an inside job. Focus. The presents are in the living room. We enter through the side gate during musical chairs." The van's radio crackled with a children's birthday playlist someone nearby was blasting. "So what's the plan for the actual kids? You can't just push a six-year-old out of the way." "We won't. We'll blend in. I bought us costumes." He revealed two crumpled outfits from the back seat, one sparkly unicorn and one saggy dinosaur. "You want me, Molly Malone, master safecracker, to wear a unicorn suit to steal a Lego set?" "It's not just Lego. It's fiscal freedom. And yes, you sparkle. Literally. I added extra glitter." Molly sighed and zipped up the unicorn suit. It squeaked. "Fine. But if anyone asks me to do a balloon animal, I'm robbing their college fund too." "Deal. Remember, we go in on three. One, two..." A child screamed with joy from the house next door. "Bill, that's not Timmy's house. That's the cops' kid. The cop who arrested us last time." "Right. So we get extra time? He'll be at work protecting Timmy's PS5?" Molly pulled off the unicorn horn and threw it at him. "We are aborting. We are not stealing from children in front of a cop's house while dressed like rejected mascots." "Okay, okay. But can we at least keep the cake? I heard it's chocolate." Outside, the bounce house deflated with a sad, long wheeze. "You get me real loot next time. Banks, museums, anything with adults who can afford to lose stuff." "Promise. But I'm keeping the unicorn suit. It really brings out my eyes." They drove away slowly, glitter trailing behind the van like criminal fairy dust. "So... still hungry for bologna?" "I will stab you with this plastic horn." And she probably would have, if the horn hadn't been so squeaky and pathetically cute. "Love you too, partner." He grinned as sirens wailed nowhere near them. "Drive, moron, before the clown finds us." "Yes ma'am." "And stop eating my sandwich."
created_at
"2026-07-25T17:34:00.952Z"
7/25/2026, 5:34:00 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
24145
moderation_latency
(null)
generation_time
27154
tokens_prompt
75
tokens_completion
765
native_tokens_prompt
225
native_tokens_completion
4790
native_tokens_completion_images
0
native_tokens_reasoning
4062
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
0.02063875
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f389fde8bec852b94fd7"
is_byok
false
latency
819
model_permaslug
"meta/muse-spark-1.1-20260709"
provider_name
"Meta"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785000840-9hHAZZ7jXbJji0usNQ8J"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000840-HWsKEqE9KgvEOn4U3nfS"
upstream_id
"resp_6a64f389fde8bec852b94fd7"
total_cost
0.02063875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
515
96.97%
Dialogue to Total Word Ratio
Ratio: 69.22%, Deviation: 0.78%
neededClean
false
wordsTotal
523
wordsDialogue
362
78.6245%