NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KREY3YBAHN36XJ5YP30Z6Q
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
25.9s
Cost:
$0.004043
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
18.3940%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 crudely drawn map across the kitchen table while Bill polished a pair of plastic princess ears with a dish towel. The target was a second floor apartment on Maple where seven year old Timmy was turning six with a bouncy castle and a suspiciously large pile of presents. The parents would be distracted by cake, the babysitter by a toddler glitter explosion, and the security was a nervous goldfish. Bill tapped the window with a spoon and said we can go in through the balcony after the songs start. Molly adjusted her inflatable unicorn costume and checked the bag full of noise makers. She asked do you have the fake mustaches ready just in case. He nodded and replied yes but they smell like cheese. They would enter through the balcony, grab the loot, and exit before the candles were blown out. Bill muttered about the moral ambiguity of stealing from children. Molly replied that charity starts at home and they were providing a service. The doorbell rang. The hallway smelled of burnt sugar and cheap air freshener. Bill slipped on his elf slippers, immediately tripped, and knocked over a stack of canned beans. Molly grabbed the map, folded it into a paper airplane, and launched it toward the fridge for inspiration. She considered the ethics of taking a stuffed dinosaur but decided the kid probably had three. Bill rehearsed his cover story about being a late relative from Finland who only speaks in birthday song lyrics. They agreed to split the haul sixty forty because Molly had to rent the unicorn costume. A siren wailed somewhere far away, which they both pretended was normal.
created_at
"2026-09-03T13:48:46.599Z"
9/3/2026, 1:48:46 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
148
moderation_latency
(null)
generation_time
25847
tokens_prompt
75
tokens_completion
2880
native_tokens_prompt
117
native_tokens_completion
2678
native_tokens_completion_images
(null)
native_tokens_reasoning
2476
native_tokens_cached
48
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
0.00404307
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443326-YrEWkiv2ZLyYMolLEUOO"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443326-G5uzl7iyg0QH6UEreHuD"
upstream_id
"oyocXb3-7ArivV-a35536c75c28c52e"
provider_responses
0
endpoint_id
"e6c588fa-aef0-4e1b-bb7f-78185dd5b6da"
id
"oyocXb3-7ArivV-a35536c75c28c52e"
is_byok
false
latency
121
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Together"
status
200
total_cost
0.00404307
cache_discount
0.00001488
upstream_inference_cost
0
provider_name
"Together"
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
278
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
278
wordsDialogue
0
18.3940%