NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5M704ABF33HH17DE0K12J
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
50.0s
Cost:
$0.037677
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
80.14%
Dialogue to Total Word Ratio
(details)
90.0699%
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 flyer across the dashboard of the getaway van, which had three flat tires, a pine air freshener that smelled like despair, and a collection of unpaid parking tickets. The flyer itself was aggressively glittery and read Princess Ella's Sixth Birthday Extravaganza! Gifts On The Living Room Table! Bill leaned over, squinting through novelty sunglasses left over from their failed magician convention heist. He flicked a piece of glitter off. "Molly, we are really going to steal presents from a six year old?" Bill asked. "Technically we are stealing from the table near a six year old. It's nuanced," Molly said. "My mom told me I'd be cursed if I ever stole from kids," Bill said. "Your mom thinks you work in finance. Her curse calibration is off," Molly replied. Outside the van, the target house was already inflating. A sagging bouncy castle wheezed in the driveway. A pile of balloons strained against a mailbox. Through the window they could see a mountain of brightly wrapped boxes, ribbons catching the sun. Bill lowered his voice like he was in a real movie. "Okay, so how do we even get inside without looking suspicious?" Bill whispered. "We wear clown costumes. Nobody questions clowns at a kids party," Molly said. "Last time we wore clown costumes you got trapped in the ball pit," Bill said. "That was reconnaissance. We bring a giant box labeled Clown Gift. We load everything into it," Molly explained. "Oh, like a Trojan horse, but with more primary colors?" Bill asked. "Exactly. You distract the kids with balloon animals while I do the heavy lifting," Molly said. "I can only make one animal and it looks like a diseased sausage," Bill admitted. "Kids have low standards. Presents are by the cake. Grab, stuff, leave," Molly said. "What about the parents? Parties are full of parents filming everything," Bill said. "Parents at kids parties are exhausted. They will thank us for removing loud toys," Molly said. "Should we leave at least one gift so she doesn't cry?" Bill asked. "We leave the boring educational spelling game. No kid wants that," Molly said. "And if there's a magician, we leave. I don't trust guys who pull rabbits," Bill declared. "Agreed. If there's a magician we rob him instead. Watches would pay rent," Molly agreed. The wind picked up and sent a loose balloon wobbling past their windshield. Somewhere inside the house, a child screamed with joy and a dog barked. Molly watched a tired dad attempt to untangle Christmas lights in July. Bill drummed his fingers on his clown nose, which squeaked. "Fine, but I get first slice of cake for hazard pay," Bill said. "You ate a plastic tiara last time calling it frosting," Molly snapped. "It said edible glitter, that was misleading advertising," Bill protested. Molly folded the flyer into her pocket and pulled the giant fake present box from the back seat, its wrapping paper already peeling. "Let's go ruin a birthday," she said.
created_at
"2026-07-25T17:37:04.523Z"
7/25/2026, 5:37:04 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
46417
moderation_latency
(null)
generation_time
49852
tokens_prompt
75
tokens_completion
757
native_tokens_prompt
225
native_tokens_completion
8799
native_tokens_completion_images
0
native_tokens_reasoning
8138
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
0.037677
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f4408bf4791008304148"
is_byok
false
latency
286
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-1785001024-YYerMhHUfVrXs1ImcHO8"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001024-nJayapNkUfOf7Z9sB6yG"
upstream_id
"resp_6a64f4408bf4791008304148"
total_cost
0.037677
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
100.00%
Matches word count
n/a
neededClean
false
words
499
80.14%
Dialogue to Total Word Ratio
Ratio: 52.10%, Deviation: 2.10%
neededClean
false
wordsTotal
499
wordsDialogue
260
90.0699%