NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KRNGRCM167CNSJ71XDPJYV
Run Details
Model:
Muse Glimmer 30B (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
44.2s
Cost:
$0.004079
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.44%
Dialogue to Total Word Ratio
(details)
43.4123%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 was taping a pink plastic tiara to her forehead with duct tape. Bill watched from the kitchen doorway holding a clipboard and a half-eaten donut. "That's not a disguise, that's a cry for help," he said. "It says I'm a birthday fairy godmother," Molly said. "The invitation said seven year old twins. Seven year olds love fairies and they love godmothers. Mostly they love presents." Bill flipped a page. "Address is Maple Court, backyard. Party starts at three. Parents will be inside watching a soccer game. One security guard, which is actually just Mrs. Henderson with a bad hip and a fly swatter." "Perfect. We go in as party entertainers. I do glitter, you do balloon animals." "You can't do balloon animals." "I learned on YouTube. It says one balloon, one twist, one existential crisis." Bill sighed. "Molly, the plan is simple. We get in, we wait for the gift table, we grab everything, we leave through the slide." "The slide is a good exit strategy. Very low profile. Also very loud." "It squeaks. We'll oil it." Molly pointed at his clipboard. "What are we taking?" "Everything. Boxes, bags, the whole table. The twins have twelve presents each. That's twenty four boxes. Plus a giant stuffed dinosaur." "Can we fit a dinosaur in the van?" "We leave the dinosaur." "You can't leave the dinosaur. It's a statement piece." "It's a ninety pound statement piece." Molly adjusted the tiara. "Fine. We take the dinosaur and we tell the parents it ran away with the other presents. It's a heist with a moral." Bill wrote that down. "You're going to moralize a robbery?" "I'm going to accessorize a robbery. Pink cape, fairy wings, the works. Kids won't question it. Adults will be too polite to say anything because I'm a woman in a tiara." "You're a woman in a tiara holding a crowbar." "It's a wand." "You taped a crowbar to a wand." "Art." Bill checked his watch. "We need to be there by two thirty. Costumes in the car." "Do we have a getaway driver?" "We are the getaway drivers. I drive, you navigate and throw candy at anyone who follows us." "Deal. Also we need a cover story for why we're leaving early." "We got a call. Another party. A birthday emergency." Molly grinned. "I love it. We steal presents and then we steal another party." "That's the spirit." Bill tossed the donut in the trash and pulled a sequined vest off the back of a chair. Molly was already spraying glitter over the kitchen table. "One more thing," she said. "If a kid cries when we take their gifts, what do we do?" "We give them a sticker." "And if they ask why the fairy is taking the presents?" Bill smiled. "You tell them the fairy needs them for a very important magic trick. And then we run." The back door banged open and the rain started.
created_at
"2026-09-03T13:52:22.294Z"
9/3/2026, 1:52:22 PM
model
"meta/muse-glimmer-30b-20260810"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
101
moderation_latency
(null)
generation_time
44147
tokens_prompt
75
tokens_completion
2667
native_tokens_prompt
117
native_tokens_completion
2715
native_tokens_completion_images
(null)
native_tokens_reasoning
1955
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
0.00407873
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788443542-Ammhfbh9G8xCtZyY4F4O"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788443542-ip0i8Co1moxWzIdvSgAT"
upstream_id
"chatcmpl-chatcmpl-547d011a553f448cb72c63431b7b0b25"
provider_responses
0
endpoint_id
"38b85376-97ef-4ae3-b2f4-b23ca1ee2495"
id
"chatcmpl-chatcmpl-547d011a553f448cb72c63431b7b0b25"
is_byok
false
latency
21
model_permaslug
"meta/muse-glimmer-30b-20260810"
provider_name
"Fireworks"
status
200
total_cost
0.00407873
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
86.38%
Matches word count
n/a
neededClean
false
words
489
0.44%
Dialogue to Total Word Ratio
Ratio: 80.41%, Deviation: 10.41%
neededClean
false
wordsTotal
490
wordsDialogue
394
43.4123%