NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRB7Y4AFYNDSQZKDSRA6G7
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
19.4s
Cost:
$0.001859
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
1.04%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.5180%
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
The rain had turned the alley behind the community center into a mirror for broken streetlights. Molly crouched under the dumpster with a clipboard and a plastic tiara perched crookedly on her head. Bill stood beside her in a reflective vest that said VOLUNTEER and held a bouncy castle pump like it was a weapon. Molly tapped the clipboard. The window for the Henderson kid’s seventh birthday was at six. Presents under a table, parents in the kitchen, three adults total and one exhausted aunt. Bill squinted at the flyer she’d printed off the neighborhood app. Pink balloons, a dinosaur cake, and a note about a prize table. Bill said, Are we really going to steal presents from seven year olds. Molly said, We are going to liberate them from consumerism before they learn to want. Bill said, That’s not what the job is. Molly said, The job is exactly what the job is. Presents under a table, easy grab, high sentimental value on the black market. A kid thinks a toy is worth a thousand dollars. Bill said, He will think his parents are the villains. Molly adjusted the tiara. We’re not stealing, we’re redistributing. The aunt is already drunk. The parents will be too busy arguing about who forgot the ice. Bill said, You have a plan for the dinosaur cake. Molly said, We leave the cake. We take the gifts. No one notices a missing Spider-Man backpack for thirty seconds when the piñata drops. Bill kicked a puddle. It splashed up the back of his vest. The plan hinges on you getting in first. Molly grinned. I’m already in. I signed up as the face painter. I have a badge. Bill said, You forged a badge. Molly said, I drew it on with a Sharpie. It’s authentic. Bill said, What if there’s a security guard. Molly said, It’s a community center. The security guard is Mrs. Kowalski who brings her own chair and naps. Bill said, What if the kids ask you for a unicorn. Molly said, I give them a very convincing unicorn. Then I slip out the back with the loot bag while they’re distracted. Bill said, You’re going to wear that tiara. Molly said, The tiara is camouflage. It says I’m harmless and professional. Bill said, You’re going to get arrested. Molly said, I’m going to get paid. Five hundred for the haul, split even, and you get to keep the bouncy castle pump. Bill said, I don’t want a pump. Molly said, You wanted a heist with no blood. This is a heist with cake. It’s perfect. A car slowed at the curb and the community center lights flickered on. Through the kitchen window they could see the presents being stacked, bright paper and ribbons piling up like a small hill. Bill exhaled. Okay. Six o’clock. You paint faces, I go in the back door when the music starts. Molly said, When the music starts I’ll be in the middle of a glitter disaster. Perfect cover. Bill said, If anyone asks, we’re just weird adults who love kids. Molly said, We are weird adults who love loot. Same thing.
created_at
"2026-09-03T13:46:45.579Z"
9/3/2026, 1:46:45 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
119
moderation_latency
(null)
generation_time
19389
tokens_prompt
75
tokens_completion
1374
native_tokens_prompt
117
native_tokens_completion
1222
native_tokens_completion_images
(null)
native_tokens_reasoning
613
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
0.00185907
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443205-4L0WZAgQ54DLq1H3F3q1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443205-nelLY40MGH1NMxuHSkYM"
upstream_id
"chatcmpl-chatcmpl-fe55971f2bbd4ae5b5c7f65522e35298"
provider_responses
0
endpoint_id
"38b85376-97ef-4ae3-b2f4-b23ca1ee2495"
id
"chatcmpl-chatcmpl-fe55971f2bbd4ae5b5c7f65522e35298"
is_byok
false
latency
22
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Fireworks"
status
200
total_cost
0.00185907
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
1.04%
Matches word count
n/a
neededClean
false
words
526
0.00%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
527
wordsDialogue
0
0.5180%