NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KR9P9ESKE6HT2P33Y83ECX
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
26.8s
Cost:
$0.002155
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.40%
Dialogue to Total Word Ratio
(details)
99.0569%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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. Bill picked at a stale cupcake. "Molly, a kids' party? Presents under a plastic tablecloth? This is a crime against Christmas spirit." "It's a crime against our rent. Six kids, six parents distracted by sugar, one giant pile of shiny boxes." "And the security?" "One bored babysitter and a Bluetooth speaker playing Baby Shark on loop." "Okay, but how do we get in?" "We don't break in. We get invited. I'm 'Aunt Molly,' you're 'Uncle Bill.' We bring the cupcakes." "Do I have to wear the dinosaur onesie?" "You volunteered for it last time." "I did not volunteer. I was blackmailed." "Fine, no onesie. But you have to do the balloon animal thing." "I can make a decent poodle." "Perfect. We grab the presents at 4 PM during the piƱata chaos, toss them in the stroller." "Stroller?" "I borrowed it. It's basically a heist van." "You're a genius, Molly." "I'm a professional." "Do we have an exit?" "Back gate, Mrs. Henderson leaves it open for the dog." "And if a kid cries?" "We cry louder. It's method acting." "I love you." "Save it for the alibi."
created_at
"2026-09-03T13:45:54.741Z"
9/3/2026, 1:45:54 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
105
moderation_latency
(null)
generation_time
26794
tokens_prompt
75
tokens_completion
1383
native_tokens_prompt
117
native_tokens_completion
1419
native_tokens_completion_images
(null)
native_tokens_reasoning
1101
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
0.00215457
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443154-d0S3UDNAkREEU7PGknut"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443154-pFcrtjjyTi3THHws1AKp"
upstream_id
"chatcmpl-chatcmpl-89739192870c48e4b893ec470db95a34"
provider_responses
0
endpoint_id
"38b85376-97ef-4ae3-b2f4-b23ca1ee2495"
id
"chatcmpl-chatcmpl-89739192870c48e4b893ec470db95a34"
is_byok
false
latency
20
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Fireworks"
status
200
total_cost
0.00215457
cache_discount
0.00001488
upstream_inference_cost
0
provider_name
"Fireworks"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
99.40%
Dialogue to Total Word Ratio
Ratio: 92.78%, Deviation: 2.78%
neededClean
false
wordsTotal
194
wordsDialogue
180
99.0569%