NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5C5042QSAJGGT5NWE1RKQ
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
1m 45s
Cost:
$0.037876
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.93%
Dialogue to Total Word Ratio
(details)
99.9252%
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 crayon-drawn map across the hood of their dented getaway van while Bill tried to look inconspicuous in a clown wig that smelled faintly of cheese. The target house pulsed with sugar-fueled chaos, balloons bobbing over the fence like fat pastel sentries and a hand-painted banner screaming HAPPY BIRTHDAY LEO in glitter that could blind a magpie. "Leo's turning six, so security will be sticky but slow." said Molly. Bill adjusted the red nose with the dignity of a man attending his own execution while a toddler pressed his face against the window and waved a juice-stained hand. "Define slow. Last time slow meant bitten by a pony." said Bill. Molly tapped the map where she had marked present table, exit route, and emergency cupcake supply with the focus of a general invading Belgium. She grinned wickedly. "Relax. We walk in as entertainers, grab the present table, vanish during cake." said Molly. A shriek erupted from the backyard as parents laughed near the grill and toddlers bounced. "I am not wearing the wig. I look like a depressed lion." said Bill. Molly yanked the rainbow wig lower over his ears and lint-rolled a suspicious cookie crumb off his fake polka-dot vest with maternal menace. "You are wearing the wig. You already smell like one." said Molly. Across the street Mrs. Alvarez patrolled her porch with binoculars, a clipboard, and the unmistakable posture of someone who had never lost at bingo. "What about the mom? She runs neighborhood watch with binoculars and grudges." said Bill. Molly waved sweetly as the woman squinted, then flipped the map over to reveal a seating chart stolen from the preschool cubbies last Tuesday. "Mrs. Alvarez? Please. I'll distract her with small talk and juice boxes." said Molly. Music thumped inside while a dog in a party hat barked. "And the kids? Thirty sugar-crazed witnesses screaming at everything shiny." said Bill. Bill peered over the fence at the mountain of wrapped boxes glinting near the garage, ribbons trembling in the breeze like colorful hostages awaiting rescue. "Kids love us. We bring balloon animals and criminal energy." said Molly. He swallowed hard while the smell of frosting and hot dogs drifted over like a delicious threat today. "Fine. But if I get glitter-bombed again, I'm keeping the Lego castle." said Bill. Molly produced two oversized gift sacks stenciled with PROPERTY OF SANTA and a forged thank-you card that read thanks for inviting us suckers. "Deal. You take Lego, I take the robot dog. Now smile, birthday boy awaits." said Molly. A chorus of children screamed as the clown car backfired, confetti cannons coughed, and Leo himself charged the gate wielding a foam sword. "Why do I feel like the piƱata is judging our life choices?" said Bill. "Because it is. Now grab the gift sacks and act like you like children." said Molly. Molly shoved a balloon poodle into his hands, straightened his nose, and marched toward the glittering chaos with the confidence of doom. Today presents fall.
created_at
"2026-09-03T08:15:12.394Z"
9/3/2026, 8:15:12 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8807
moderation_latency
(null)
generation_time
104939
tokens_prompt
75
tokens_completion
794
native_tokens_prompt
68
native_tokens_completion
8892
native_tokens_completion_images
0
native_tokens_reasoning
8176
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
0.037876
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423312-GzkJpWxQNVhuN709uFUY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423312-dU0u22tTKu83morjpF5Z"
upstream_id
"resp_6a992c966387928d1788472c"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992c966387928d1788472c"
is_byok
false
latency
5857
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.037876
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
503
99.93%
Dialogue to Total Word Ratio
Ratio: 29.88%, Deviation: 0.12%
neededClean
false
wordsTotal
512
wordsDialogue
153
99.9252%