NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD80A6KR4S508P44XR0PTAZ
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
16.6s
Cost:
$0.011782
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9595%
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 blueprint across the van hood, revealing not a bank but Mrs. Henderson's backyard, complete with bouncy castle, clown, and a folding table labeled TARGET RICH. Bill squinted at the crayon-drawn Xs marking laser tripwires, which were actually garden hoses. The plan relied on disguises. Molly had acquired two enormous mascot costumes, one bear, one slightly deflated elephant. Bill tapped the elephant trunk. "We agreed no more jobs involving children or mascots." Molly grinned, adjusting her bear head. "Relax, it's just aggressive borrowing from very small rich people." Bill sighed. The real obstacle wasn't the clown, who was clearly ex-military based on his balloon-animal aggression, but the presents themselves, stacked like Fort Knox behind a juice-box moat. Their getaway driver, a teenager named Kevin, had already been bribed with cake. Molly checked her watch. The magician was about to start, providing perfect distraction. Bill zipped the costume, sweating instantly. He whispered through fiberglass. Operation Birthday Blitz was officially underway. Bill regretted everything as confetti cannons armed themselves. Molly waddled toward the gate, waving enthusiastically at terrified toddlers. He followed, trunk dragging, dignity abandoned, muttering "Fine." The clown stared, twisting a giraffe with unsettling precision like a warning tomorrow never comes quickly
created_at
"2026-07-25T18:18:38.172Z"
7/25/2026, 6:18:38 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15134
moderation_latency
(null)
generation_time
16566
tokens_prompt
75
tokens_completion
356
native_tokens_prompt
225
native_tokens_completion
2706
native_tokens_completion_images
0
native_tokens_reasoning
2407
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
0.01178175
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64fdfec58836debdbb4487"
is_byok
false
latency
420
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-1785003518-qLxtkh1yBjWzOxSpbcgW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003518-dYsiO5jjvOcQbHxc3LqI"
upstream_id
"resp_6a64fdfec58836debdbb4487"
total_cost
0.01178175
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
99.92%
Matches word count
n/a
neededClean
false
words
203
100.00%
Dialogue to Total Word Ratio
Ratio: 9.71%, Deviation: 0.29%
neededClean
false
wordsTotal
206
wordsDialogue
20
99.9595%