NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K570DVF7WA0R00HV1XET9D
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
38.7s
Cost:
$0.030859
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.80%
Dialogue to Total Word Ratio
(details)
99.9017%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 50% 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
The van smelled of old pizza and regret. Molly tapped the blueprint spread across the dashboard while Bill tried to fit a clown wig over his bald head. Outside the pastel brick community center, a banner read HAPPY 6TH BIRTHDAY JAYDEN with a lopsided dinosaur. A clown bounced near the entrance twisting balloons, and a table inside sagged under a mountain of brightly wrapped presents. "You cannot be serious about the wig," Molly said. "It is camouflage," Bill said. "Every children's party has a creepy clown. I will blend in perfectly." "You blend in like a tax audit at a petting zoo. Take it off before someone calls the police preemptively." Bill sighed and peeled the synthetic rainbow hair off his scalp, revealing a sweaty shine. Molly unfolded her plan, which was drawn on the back of a takeout menu in aggressive red marker. "So we walk in during the musical chairs chaos," Bill said. "Grab the loot and walk out?" "No, we will be subtle," Molly said. "You will distract the parents with your natural charm, which is to say you will talk until they beg for mercy, and I will swap the presents with identical decoys." "You made decoy presents?" "I wrapped cereal boxes last night. They look fantastic from three feet away in dim lighting while children are screaming." Bill peered through the windshield at the towering pile of gifts. Some were taller than the birthday boy himself. "That kid is six and richer than us," Bill said. "Look at that box. That is a bicycle." "Focus. The window on the east side is always unlocked because the janitor props it with a juice box," Molly said. "We slip in at cake time. Everyone sings, eyes closed, off-key. Thirty seconds of social blindness." "What about the clown?" Bill asked. "The clown is our exit strategy," Molly said. "You will pay twenty bucks to cause a diversion." "I thought I was the clown." "You are the backup clown. He is the primary clown. Do not confuse the hierarchy." Bill nodded solemnly, as if receiving sacred knowledge. He pulled two oversized gift bags from the back seat, both printed with nauseatingly cheerful dinosaurs. "And if we get caught?" Bill said. "We will say we are performance artists hired to teach children about income inequality," Molly said. "No jury would convict." "Brilliant. Will we at least get cake?" "If we do this correctly, we get cake and a train set." Molly checked her watch. Inside, the lights dimmed as six candles flickered to life. The off-key chorus began to rise, wobbly and earnest. The parents clapped along out of rhythm, the dinosaur mascot wobbled dangerously near the frosting, and the scent of sugar and wrapping paper hung thick in the humid air while Jayden stared intensely at his future empire. "Now," she whispered. They slipped from the van, decoy bags rustling, ready to rob the most heavily guarded fortress of all, a room full of six-year-olds hopped up on sugar.
created_at
"2026-09-03T08:12:23.873Z"
9/3/2026, 8:12:23 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3380
moderation_latency
(null)
generation_time
38638
tokens_prompt
75
tokens_completion
779
native_tokens_prompt
68
native_tokens_completion
7241
native_tokens_completion_images
0
native_tokens_reasoning
6547
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
0.03085925
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423143-so1pmptHyDQXSTyvRh6d"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423143-OpNwObKniUgKh0fZZ35d"
upstream_id
"resp_6a992be811845d41ead14948"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992be811845d41ead14948"
is_byok
false
latency
404
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.03085925
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
500
99.80%
Dialogue to Total Word Ratio
Ratio: 49.80%, Deviation: 0.20%
neededClean
false
wordsTotal
504
wordsDialogue
251
99.9017%