NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6DT080TNDK8JMM7KTXGKC
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.006559
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
79.31%
Dialogue to Total Word Ratio
(details)
89.0110%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, remind me again why we're robbing a six-year-old?" Bill whispered. "Because, Bill, little Timmy's pile of presents is worth more than the bank job," Molly hissed. "Right, but it's a kids party, there's gonna be clowns, balloons, screaming." "Exactly, perfect cover, nobody suspects two adults in clown makeup." "Wait, we have clown makeup? You didn't mention clown makeup." "I bought it, extra large shoes, red noses, everything, it's foolproof." "Foolproof? Last time you said foolproof we got stuck in a bouncy castle for three hours." "That was reconnaissance, this time we walk in, grab the Paw Patrol tower and run." "What about the parents? And the actual clown they hired?" "We tell them we're the backup clowns, support clowns, emotional support clowns." "Oh god, Molly, there's a mom staring right at us." "Quick, act natural, juggle something, juggle your guilt about stealing from children." "I can't juggle, I'm having a moral crisis here." "Save it, grab the loot, I want that blue bicycle." "Fine, but if we get caught, you're explaining to my mother why I'm in jail for stealing Legos," Bill muttered. "Mother? Please, you'll be a legend, the Hamburglar of birthdays."
created_at
"2026-07-25T17:51:03.182Z"
7/25/2026, 5:51:03 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7919
moderation_latency
(null)
generation_time
9188
tokens_prompt
75
tokens_completion
302
native_tokens_prompt
225
native_tokens_completion
1477
native_tokens_completion_images
0
native_tokens_reasoning
1184
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
0.0065585
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f78726761e2a8c8242a9"
is_byok
false
latency
353
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-1785001863-4q93s1uxrMOkSnBuZY05"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001863-keFl6UFym7y6fYw82HWm"
upstream_id
"resp_6a64f78726761e2a8c8242a9"
total_cost
0.0065585
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
194
79.31%
Dialogue to Total Word Ratio
Ratio: 96.94%, Deviation: 6.94%
neededClean
false
wordsTotal
196
wordsDialogue
190
89.0110%