NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6Q05AFG6PCA5WCW3KY71H
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
11.0s
Cost:
$0.005870
Provider:
Meta
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 30% 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 blueprint across the sticky diner table. It was a crayon drawing of a bounce house taped to a Chuck E. Cheese placemat, with X MARKS THE PRESENTS written in glitter glue. Bill stared at it for a long time, his coffee going cold. "This is your big score?" he said. Molly tapped the glitter X with a chipped red fingernail. "This is seven-year-old Timmy Henderson's birthday. His mom went viral on TikTok for extreme present piles. We're talking last year's pile was taller than Timmy." Bill leaned back. "So we're stealing from a child now? Our reputation. We used to have standards." "We have debts," Molly said. "And this is market research. I went to the park. I counted. There are at least forty wrapped boxes in that living room. One of them is shaped like a bike." The waitress refilled their coffees and eyed the blueprint. Molly quickly covered it with the syrup menu. Bill lowered his voice. "Okay, walk me through this genius plan. How do we get past security?" "It's a children's party, Bill. Security is a dad named Gary in a 'Best Dad Ever' apron flipping burgers." "Gary's can be dangerous," Bill muttered. "They have tongs. And opinions about charcoal." Molly ignored him and pointed to a scribbled side entrance. "The invitation says three PM, backyard entrance, clown arrives at three thirty. We arrive at three fifteen dressed as additional entertainment. I saw it on Pinterest. Everybody expects extra clowns." "We don't own clown suits." "We own shame, which is close enough. I got us vests from the thrift store. You can be Balloons Bill. I'll be Face Paint Molly." Bill looked physically pained. "I don't know how to make balloon animals. Last time I tried I made what a health inspector called a raw sausage." "You just twist until it squeaks and hand it to a kid and run. The point is distraction. While they are all watching you have an existential crisis with latex, I grab the present table." Bill frowned at the glitter map. "What about the kids? Kids are perceptive. They know when you're lying. Especially about cake." "Which is why you will also be in charge of cake security," Molly said. "You stand near the cake and look official. No one questions a man near a cake if he looks worried enough." "And the getaway?" Molly smiled and slid a key across the table. It had a My Little Pony keychain on it. "I've rented a minivan. It has a built-in DVD player. Very discreet." Bill picked up the key like it might bite him. "Molly, what if Timmy cries? I can't handle it if Timmy cries. I still feel bad about taking that garden gnome." "He won't cry. He's getting forty presents. He won't even notice if two or three or all of them are replaced with our laundry as decoys." "That's your plan? Laundry decoys?" "It's eco-friendly crime," she said. "Reduce, reuse, steal a bike." A long silence settled. Outside, a real clown walked past the diner window carrying dry cleaning. It felt like a sign. Bill sighed and folded the blueprint, getting glitter all over his sleeves. "Fine," he said. "But if I have to make one balloon poodle, I want the bike." Molly grinned. "Deal. You can ride it away from all our terrible choices."
created_at
"2026-07-25T17:56:04.402Z"
7/25/2026, 5:56:04 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4673
moderation_latency
(null)
generation_time
10640
tokens_prompt
75
tokens_completion
813
native_tokens_prompt
225
native_tokens_completion
1315
native_tokens_completion_images
0
native_tokens_reasoning
567
native_tokens_cached
0
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
"completed"
service_tier
"auto"
usage
0.00587
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f8b4484d730bbb884f3e"
is_byok
false
latency
350
model_permaslug
"meta/muse-spark-1.1-20260709"
provider_name
"Meta"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1785002164-Yd7r2SWBtUT6Bnj0szjg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002164-Jy2oFIqNuJ2raY4Hqs45"
upstream_id
"resp_6a64f8b4484d730bbb884f3e"
total_cost
0.00587
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
561
0.00%
Dialogue to Total Word Ratio
Ratio: 69.03%, Deviation: 39.03%
neededClean
false
wordsTotal
565
wordsDialogue
390
0.0000%