NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRKQGHFMGR6P6DMRJ0CJYX
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
17.8s
Cost:
$0.001658
Provider:
Fireworks
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 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 the flyer across the kitchen table and tapped the glitter glue with a pen. The invitation to Timmy's Seventh Birthday Extravaganza showed a castle made of cupcakes and a promise of goodie bags for everyone. Bill was already wearing a fake mustache and a plastic badge that said Party Inspector. The plan was simple until it wasn't. She read the details out loud while he tried to eat a cold pizza without getting cheese on the badge. Timmy's house, Saturday four o'clock, bounce house in the backyard, parents out for an hour. Presents on the dining room table. No security except a very tired Labrador named Sir Barks. Bill swallowed and said the mustache was itching. Molly said it was working. He said it was working like a flag that says professional thief inside. She said the whole point was to look official. You walk in, you check the cake for health violations, you pocket the presents while nobody is looking. Bill said the parents were looking. They were always looking. Molly said the parents would be at the bar. The invitation said drop off and dash. He said that was a lie. Parents never dash. Parents hover by the punch bowl with a wet napkin and a spreadsheet of allergies. She said then we use the kids. Kids are excellent distractions. You hand them a sticker, they scream, nobody notices you lifting a glittery unicorn scooter. Bill said it was a scooter. That was a lot to lift. Molly said we take the small stuff. Cards, robots, the Build-A-Dinosaur kits. The scooter stays. He said you said all the presents. She said all the presents that fit in a tote bag. Bill adjusted the badge and said the Labrador was a problem. Molly said Sir Barks was listed as friendly and food motivated. We bring treats. He said we are not bringing treats for a dog we are about to rob. She said we are bringing treats for a dog we are befriending. Big difference. Bill said the difference was approximately zero. Molly said fine, then you handle the dog, I handle the presents. He said I am handling the mustache, the badge, and my dignity. She said dignity is heavy. Leave it in the car. Bill sighed and pointed at the flyer. The party theme was Space Explorers. That meant everyone would be wearing silver helmets. Molly said perfect cover. We wear silver helmets. He said we have no silver helmets. She said we have aluminum foil and two paper plates. Bill said that was a plan he could respect.
created_at
"2026-09-03T13:51:23.673Z"
9/3/2026, 1:51:23 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
106
moderation_latency
(null)
generation_time
17707
tokens_prompt
75
tokens_completion
1292
native_tokens_prompt
117
native_tokens_completion
1101
native_tokens_completion_images
(null)
native_tokens_reasoning
668
native_tokens_cached
112
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
0.00165773
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443483-afwqxI2CdjNGpRWzqZYr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443483-VBxRIhEIXGL7iVJ38VAi"
upstream_id
"chatcmpl-chatcmpl-ca67498818994578b2318fddc95e3e6d"
provider_responses
0
endpoint_id
"38b85376-97ef-4ae3-b2f4-b23ca1ee2495"
id
"chatcmpl-chatcmpl-ca67498818994578b2318fddc95e3e6d"
is_byok
false
latency
22
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Fireworks"
status
200
total_cost
0.00165773
cache_discount
0.00003472
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
0.00%
Matches word count
n/a
neededClean
false
words
434
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
436
wordsDialogue
0
0.0000%