NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRJC7NNXGMZ80GPCXDFT8S
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
44.9s
Cost:
$0.003051
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.28%
Dialogue to Total Word Ratio
(details)
99.6010%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 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 a crayon drawing of a birthday castle across the kitchen table while Bill tested the grappling hook on a laundry basket. The target was seven-year-old Timmy’s surprise party, held in a backyard with a bouncer made of balloons and a parent patrol. She tapped the paper with a marker. Outside, the sprinklers ticked on and off, and a kazoo solo drifted from the bounce house. Bill had rented a clown costume, but the shoes squeaked. Molly had a plan involving a piñata, a distraction, and a van disguised as an ice cream truck. "We can't just waltz in. Timmy's mom hired two uncles for security." "Uncles are just grown men who fell asleep on lawn chairs." "They have walkie-talkies and a mean inflatable dinosaur." "Perfect, we'll be the birthday magician and his assistant." "Fine, you do the rabbit, I'll grab the presents while they watch the trick." "And if a kid cries?" "We cry louder and blame the clown shoes." "Do we have a bag big enough for twenty LEGO sets and a karaoke machine?" "I brought the stroller, it's basically a rolling loot vault." "What about the glitter?" "Glitter is the real heist. It gets everywhere and never comes back."
created_at
"2026-09-03T13:50:39.357Z"
9/3/2026, 1:50:39 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
261
moderation_latency
(null)
generation_time
44831
tokens_prompt
75
tokens_completion
2677
native_tokens_prompt
118
native_tokens_completion
2769
native_tokens_completion_images
(null)
native_tokens_reasoning
2489
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
0.00305088
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443439-B7JthXCj9gLgXlm8z3TA"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443439-CgRokfI150oY7aMtUVRc"
upstream_id
"req_8969d9904be8083efff064d789be439c"
provider_responses
0
endpoint_id
"6244f10e-1e45-488b-a47f-f575e0edd12b"
id
"req_8969d9904be8083efff064d789be439c"
is_byok
false
latency
217
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Phala"
status
200
total_cost
0.00305088
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
99.92%
Matches word count
n/a
neededClean
false
words
203
99.28%
Dialogue to Total Word Ratio
Ratio: 52.91%, Deviation: 2.91%
neededClean
false
wordsTotal
206
wordsDialogue
109
99.6010%