NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5K04AD90979XXMQYJ4HYV
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
24.3s
Cost:
$0.015730
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
99.34%
Dialogue to Total Word Ratio
(details)
99.0254%
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 spread the construction paper blueprint across their cluttered kitchen table and pinned it down with two juice boxes and a half eaten granola bar. Outside the window the neighbor's dog was barking at the clown costume hanging on the laundry line like a warning. "Okay, Bill, this is Timmy Patterson's seventh birthday. Bouncy castle on the left, present table on the right, near the side gate. Our exit." Bill stared at the crayon drawing which featured several crying stick figures and one very large angry mom labeled Linda. "You drew the bouncy castle as a deathtrap with teeth." "It is a deathtrap, Bill. My source says it hasn't been safety checked since twenty nineteen. We go around it." "Your source is your eight year old nephew." "He's on the inside, Bill. He says there are forty seven presents, mostly LEGO, and one big rectangular one that is definitely a Nintendo Switch." He adjusted his sunglasses indoors because he thought it made him look more criminal and less like an unemployed magician. "So we just walk into a yard full of seven year olds and steal their birthday loot? They will bite us." "That's why you wear the clown suit. You will be Distracto the Clown, you make balloon animals until they pass out from joy." "Last time I wore that suit three kids cried and a cop tased me. I am not doing clown again." "That was market research. This time you twist poodles and I go in as Party Mom with the apple cardigan and the sad store bought cupcakes." "You don't look maternal. You look like you would steal a child's juice box." Molly tapped the present table with a manicured nail and then sighed when her tote bag that read Live Laugh Larceny tipped over. "Perfect. While you are inflating giraffes I will load the presents into the wagon. We tell the parents it's for piƱata cleanup." "The wagon's wheel is broken. It goes clunk clunk clunk all the way down the street." "It adds suspense. We arrive at three fifteen, right after cake, right before the sugar crash tantrums. Peak present vulnerability." "What about Linda? Timmy's mom bench presses refrigerators. She will snap us like twigs." "My nephew hacked her grocery list. She leaves for juice boxes at three fifteen. We have six minutes." "He looked at the fridge, Molly. That is not hacking." The little red wagon by the door squeaked as if agreeing with Bill and the whole apartment smelled faintly of cupcake frosting and bad decisions. "Potato potahack. Six minutes, in and out. We take the Switch, we take the LEGOs, we leave the socks and educational books. We have standards." "And if a kid catches us red handed?" "We say we're Santa's quality control elves. Kids believe anything. My nephew thinks you charge an iPad in the microwave." Molly folded the blueprint carefully and tucked it into the tote just as both juice boxes burst.
created_at
"2026-07-25T17:36:24.72Z"
7/25/2026, 5:36:24 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21531
moderation_latency
(null)
generation_time
24221
tokens_prompt
75
tokens_completion
727
native_tokens_prompt
225
native_tokens_completion
3635
native_tokens_completion_images
0
native_tokens_reasoning
2997
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
0.01573
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f419608cd09391d84b76"
is_byok
false
latency
646
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-1785000984-wW4gIdDuniqrc0az6bZ9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000984-otrk6ayI6tJkVM85E7BW"
upstream_id
"resp_6a64f419608cd09391d84b76"
total_cost
0.01573
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
98.71%
Matches word count
n/a
neededClean
false
words
494
99.34%
Dialogue to Total Word Ratio
Ratio: 69.64%, Deviation: 0.36%
neededClean
false
wordsTotal
494
wordsDialogue
344
99.0254%