NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6JPJ6P368XE67617GZPDM
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
24.6s
Cost:
$0.015738
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9753%
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 warehouse smelled of stale coffee and cardboard. Molly spread the blueprints across a milk crate while Bill tried to untangle a string of leftover birthday lights. Outside, rain hammered the corrugated roof. Inside, the heist of the century was being planned with serious intensity and questionable morals. The target was not a bank. It was seven-year-old Timmy Henderson's backyard birthday, which according to Bill's cousin's Facebook post, was expected to have at least thirty presents, including a rumored limited edition gaming console. Molly tapped the drawing of the bounce house. Bill nodded solemnly, as if studying nuclear launch codes. Both wore leather jackets that squeaked. Neither had ever stolen from a child before, but rent was due and principles were negotiable. "Okay, walk me through it again. How do we bypass the clown?" "We don't bypass the clown. We become the clown." "You want me to dress as a clown? Bill, I have a strict no face-paint policy since the aquarium incident." "That fish bit you because you tried to steal it. This is different. Kids love clowns. Parents fear questioning them." Bill pulled out two duffel bags embroidered with My Little Pony. Molly stared, then sighed. It was perfect camouflage. No one suspects a grown man with a pastel pony bag. He also produced two squeaky red noses. Molly immediately confiscated both. "Fine. So I distract with balloon animals while you grab the gift table?" "Exactly. I'll be dressed as the magician. Big hat, cape, deep pockets. I make the presents disappear. Classic misdirection." "What about Timmy's mom? She posted she has a guard dog. A very large, very angry poodle named Princess." "Princess is all bark. I brought organic peanut butter treats. I also brought this laser pointer for maximum chaos." Outside, a minivan drove past blasting Baby Shark. It felt like an omen. Molly folded the blueprints into a pizza box for discretion. Bill practiced his magician laugh, which sounded exactly like a cough. They were ready. Or as ready as two broke adults preparing to rob a bounce house could ever be. "This plan is insane. We're stealing Paw Patrol toys from children. My mom would be so disappointed. Then she'd ask for a cut." "Think about the resale value. That console alone pays rent. The rest we can donate. Or keep. Mostly keep." "Alright. We go in at three, during musical chairs. Nobody watches gifts during musical chairs. It's proven science." "And if we get caught, we say we're performance artists teaching kids about the fleeting nature of material possessions." They bumped fists. The plan was terrible, elaborate, and slightly sticky from the birthday lights. Exactly how the best heists begin. "Wow. That's actually brilliant. For you. Okay, let's steal some joy." "One more thing. If anyone offers cake, we take it. Professional courtesy." "Obviously. I'm a thief, not a monster." Molly grinned. Bill grinned. Princess the poodle barked somewhere far away. Time slowed. "Happy birthday to us, then." "Happy birthday to us indeed."
created_at
"2026-07-25T17:53:43.502Z"
7/25/2026, 5:53:43 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
21664
moderation_latency
(null)
generation_time
24496
tokens_prompt
75
tokens_completion
780
native_tokens_prompt
225
native_tokens_completion
3637
native_tokens_completion_images
0
native_tokens_reasoning
2954
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
0.0157385
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f827eb296fb237914eb8"
is_byok
false
latency
398
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-1785002023-CtDKPQQ8EsyIMgwEU3OV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785002023-8sUl0QAAGQS3QYXrmqXW"
upstream_id
"resp_6a64f827eb296fb237914eb8"
total_cost
0.0157385
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
100.00%
Matches word count
n/a
neededClean
false
words
500
99.95%
Dialogue to Total Word Ratio
Ratio: 49.90%, Deviation: 0.10%
neededClean
false
wordsTotal
503
wordsDialogue
251
99.9753%