NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KS181AYGGRGWEYGKKWAN2P
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
26.2s
Cost:
$0.001784
Provider:
Phala
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
75.9627%
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 taped a glitter-covered invitation to the refrigerator and stared at it like it was a blueprint for a bank vault. Bill arrived with a backpack full of noise-canceling headphones, a deflated pool float, and a suspiciously large collection of juice boxes. The target was Timmy's seventh birthday. The house on Maple had a fence, a bored babysitter, and a living room the size of a warehouse filled with wrapped boxes that glittered under paper lanterns. Molly had cased it twice disguised as a balloon vendor. She adjusted her wig, a pink bob that squeaked. Bill tested his disguise, a foam dinosaur costume that smelled faintly of wet dog. "This is either genius or child endangerment," Bill whispered. "I vote both." Molly smiled. "We go in at eight, grab the gifts, leave the cake." The plan involved the float, the headphones, and a very convincing sob story about a lost puppy. The float would be their escape raft through the kiddie pool. The headphones would let them hear the babysitter's podcast. The puppy story was Molly's specialty. She had once cried on cue for a raccoon. Bill checked his watch and zipped the backpack. Outside, balloons drifted like guilty witnesses. Molly took a deep breath and practiced her party voice, which sounded suspiciously like a chipmunk.
created_at
"2026-09-03T13:58:46.577Z"
9/3/2026, 1:58:46 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
276
moderation_latency
(null)
generation_time
26137
tokens_prompt
75
tokens_completion
1662
native_tokens_prompt
118
native_tokens_completion
1617
native_tokens_completion_images
(null)
native_tokens_reasoning
1323
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
0.00178368
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443926-ac6xWIq9Ey7MqbbHE08O"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443926-rYKq3pe7lYPOsegcZD9B"
upstream_id
"req_98857ef2c2802d0f9059287d496de6b8"
provider_responses
0
endpoint_id
"6244f10e-1e45-488b-a47f-f575e0edd12b"
id
"req_98857ef2c2802d0f9059287d496de6b8"
is_byok
false
latency
234
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Phala"
status
200
total_cost
0.00178368
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
51.93%
Matches word count
n/a
neededClean
false
words
216
100.00%
Dialogue to Total Word Ratio
Ratio: 9.63%, Deviation: 0.37%
neededClean
false
wordsTotal
218
wordsDialogue
21
75.9627%