NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K57M94PTKHRKDHNCA6SEK3
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
30.1s
Cost:
$0.011768
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 cracked birthday map across the getaway van hood while Bill polished his lockpick with a lollipop. The suburban house ahead throbbed with squealing children, bouncy castle wheezes, and a clown who was clearly underpaid. Operation Party Crash demanded elegance, stealth, and total disregard for nap time. Molly tapped three entry points with a crayon stolen from last week's restaurant job. Bill nodded gravely, adjusting his fake mustache that kept drooping into his juice box straw. They had cased the joint for days, learning balloon animal weaknesses, cupcake rotation schedules, and the birthday boy's ruthless guard dog, actually a sleepy pug named Sprinkles. Molly whispered, "We need clown disguises and extra large bags tonight." Bill groaned through frosting smeared binoculars as he watched mountains of brightly wrapped presents stack dangerously near an open window. The plan was gloriously stupid: infiltrate during musical chairs, befriend the magician, then vanish with loot before cake. Bill muttered, "I hate kids, cake, and tiny chairs, remember that." Molly grinned, handing him squeaky shoes and a party hat wired with a camera. Sprinkles snored on duty. Sirens of laughter erupted inside. Molly winked, "Just smile." They waddled toward glittery doom holding sweaty hands.
created_at
"2026-09-03T08:12:44.201Z"
9/3/2026, 8:12:44 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3369
moderation_latency
(null)
generation_time
30093
tokens_prompt
75
tokens_completion
426
native_tokens_prompt
68
native_tokens_completion
2749
native_tokens_completion_images
0
native_tokens_reasoning
2370
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
0.01176825
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423164-v5nxeFbXCK4K2uJZ4Gt1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423164-eq8sGHmRwmeYrUtV1eze"
upstream_id
"resp_6a992bfca6f28dadf5814d60"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992bfca6f28dadf5814d60"
is_byok
false
latency
504
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.01176825
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%