NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD7JNM05XP0J3V24SW7F7AQ
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
31.9s
Cost:
$0.025743
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9352%
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
Molly spread the blueprints across the kitchen table revealing a bouncy castle fortress surrounded by juice boxes. "Okay, Bill, we hit the Johnson kid's birthday at fourteen hundred hours." Bill squinted at the crayon-drawn map, his face scrunched like he'd been asked to solve quantum physics. "Remind me again why we're robbing a six-year-old?" Molly tapped the pile of presents in the center with a laser pointer she stole from a cat. "Because last year that pile was worth four hundred bucks in Paw Patrol merchandise alone." Bill poured himself more cereal, missing the bowl entirely. "Right, but there's going to be parents, clowns, and, god help us, children." "We go in as entertainers, Bill. Classic Trojan horse." "Last time you said Trojan horse you actually tried to bring a horse into the library." Molly produced two crumpled costumes from a duffel bag that smelled faintly of old glitter. "You will be Mr. Wiggles the clown, I will be Princess Sparkle-Butt the Magnificent." Bill held up the tiny tutu that was clearly meant for a child. "Molly, this won't fit. My butt is not sparkly nor magnificent." "Fine, you be Princess, I'll be the clown. Focus on the presents, not fashion." The plan was simple, which meant it would certainly go terribly wrong before anyone got cake. "So we walk in, distract them with balloon animals, grab the loot, and vanish?" "Exactly. While you make a poodle, I back the van up to the present table." Bill attempted to inflate a balloon and immediately turned purple and dizzy. "Molly, what if they want us to actually entertain? I don't know any kids songs." "Just sing whatever, they won't notice. They're hopped up on sugar and screaming." Molly checked her watch, a plastic one with dinosaurs on it she'd taken from evidence. "We have twenty minutes before the piƱata breaks and chaos reigns. That's our window." Bill finally got the balloon inflated, then let it go with a squeal. "I still think the Antwerp diamond heist would have been less humiliating." "Less humiliating, Bill, but did Antwerp have unlimited pizza rolls? I think not." Molly unrolled a second sheet showing laser tripwires made of crepe paper and a guard dog that was actually a very judgmental chihuahua. "The chihuahua is the real security. My cousin lost an ankle that way." Bill nodded solemnly, because he too respected the ancient power of small angry dogs. The kitchen smelled of coffee and desperation, the official perfume of all great criminal masterminds. "Do we at least get cake after we steal everything?" Molly stared at him as if he had asked whether water was wet. "Bill, we get all the cake. That is the secondary objective." Outside, a minivan full of screaming children drove past, a terrifying omen of what awaited them. "I was against the clown shoes from the start." Both of them looked at the tiny shoes, which squeaked ominously even without anyone wearing them. Molly sighed and folded the blueprints into a pizza box.
created_at
"2026-07-25T18:11:11.113Z"
7/25/2026, 6:11:11 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
29033
moderation_latency
(null)
generation_time
31799
tokens_prompt
75
tokens_completion
770
native_tokens_prompt
225
native_tokens_completion
5991
native_tokens_completion_images
0
native_tokens_reasoning
5312
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
0.025743
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64fc3fdcf150e61a24411c"
is_byok
false
latency
384
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-1785003071-XwxY4MdaUnPcmTnPfXcq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785003071-1zSCgCv2CIw7LlbH0pVv"
upstream_id
"resp_6a64fc3fdcf150e61a24411c"
total_cost
0.025743
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
503
99.95%
Dialogue to Total Word Ratio
Ratio: 50.10%, Deviation: 0.10%
neededClean
false
wordsTotal
507
wordsDialogue
254
99.9352%