NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRY86YJDZ5W90N0WQ7VQDX
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
25.5s
Cost:
$0.001745
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
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 flyer across the kitchen table like it was a blueprint for a bank vault. The paper was glitter glue and crayon, a birthday invitation for Timmy Chen, age six, seven o'clock Saturday, 12B Maple Court. There were hand drawn cupcakes and a smiley face that looked suspiciously like a ransom note. Bill picked up a peanut butter sandwich and stared at it as if it might contain answers. The plan was simple on paper and catastrophic in practice. Get in, get the presents, get out before the ice cream melts and the parents start asking questions. Molly had already cased the block twice, noted the plastic inflatable castle in the driveway and the mother who answered the door with a casserole and a smile that never wavered. She tapped the flyer with a red pen. The back door was unlocked during the party because the kitchen was small and the adults were always running back and forth. The presents would be piled in the living room, unguarded for at least twenty minutes while Timmy opened them on camera. Bill would be the distraction, Molly would be the bag. Bill swallowed and frowned. He was sixty three, had a bad knee and a collection of novelty mugs, and he had not committed a crime since the great office printer toner heist of 1998. That was one job, Molly said. This is seven. Seven kids, seven presents, seven potential witnesses who believe in the tooth fairy and the police. He set the sandwich down. We are not stealing from kids, Bill said. We are liberating them from consumerism. You are liberating them from a plastic lightsaber, she said. I am liberating us from rent. She pulled out a second sheet, a hand drawn map of the living room with X marks. The presents would be stacked by the window. The dog was a beagle named Pickles who slept through everything except squirrels. The mother would be in the kitchen refilling juice boxes. The father would be trying to fix the bouncy castle blower. Bill rubbed his knee. What if Timmy cries. Then we cry harder, Molly said. It's called method acting. She laid out the costumes. Bill would be a birthday party magician, complete with a fake mustache and a hat that could hold a small action figure. Molly would be the overenthusiastic aunt from out of town who brought an extra piñata. Do you have an extra piñata, Bill asked. I have a tote bag, she said. It holds a lot of piñata. The window was the exit. The inflatable castle provided cover. The whole operation would take nine minutes if nobody asked for a high five. Molly had timed it with her phone while pretending to be lost. You realize this is the dumbest thing we have ever done, Bill said. We stole a commemorative plate from a nursing home, Molly said. This is more dignified. He looked at the flyer again, at the careful crayon writing and the list of songs for the playlist. Twinkle Twinkle Little Star. Baby Shark. He sighed. Fine, he said. But if I get arrested I am telling them you forced me. Only if you want me to deny it, she said, and she was already zipping the tote bag shut.
created_at
"2026-09-03T13:57:08.453Z"
9/3/2026, 1:57:08 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
279
moderation_latency
(null)
generation_time
25471
tokens_prompt
75
tokens_completion
1811
native_tokens_prompt
118
native_tokens_completion
1582
native_tokens_completion_images
(null)
native_tokens_reasoning
891
native_tokens_cached
117
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
"stop"
service_tier
(null)
usage
0.00174518
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443828-Y86CNmictGgWHsqfPtVl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443828-mjcP2muZJzgYACeltZ3O"
upstream_id
"req_4a0a1727bc589306778f53b686a266ff"
provider_responses
0
endpoint_id
"6244f10e-1e45-488b-a47f-f575e0edd12b"
id
"req_4a0a1727bc589306778f53b686a266ff"
is_byok
false
latency
236
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Phala"
status
200
total_cost
0.00174518
cache_discount
0.00003042
upstream_inference_cost
0
provider_name
"Phala"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
550
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 30.00%
neededClean
false
wordsTotal
550
wordsDialogue
0
0.0000%