NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5VVSPJ1SJ57RVD3HPZB3S
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
40.2s
Cost:
$0.029968
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
95.83%
Dialogue to Total Word Ratio
(details)
97.6017%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 70% 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 getaway van smelled faintly of cheese sticks and felony. Molly spread the Evite across the dashboard like it was the floor plan to Fort Knox. "Okay, explain Operation Birthday PiƱata again, Bill, so I can be sure we're officially the worst criminals in the city." "It's brilliant, Molly. Lisa's kid is turning six. She bought forty presents. One is definitely a PS5. We take it, sell it, pay rent." Bill wore a clown wig that was actively shedding onto the pizza boxes behind them. "Bill, last time you said brilliant we robbed the aquarium and came home with a penguin and a restraining order." "That penguin knew too much. Look, it's simple. We dress as clowns. No one questions clowns at a kids party." Molly stared at the wig, then at Bill's serious face, which was somehow worse. "You want us to infiltrate a bouncy castle full of six-year-olds in flammable wigs to steal a Switch that doesn't exist?" "It exists. I saw the wishlist. Laser tag, a bike, and a gift card that could buy us dignity." "The plan says you distract parents with balloon animals while I stuff presents into the giant cake box." Outside, the wind tried to rip the antenna off the van. Inside, Bill tried to make a balloon giraffe. "Exactly! You make a bunny, you make a poodle, you make a delayed exit with stolen Hatchimals. Look, giraffe!" "Bill, that's just a long balloon filled with despair. Those kids will turn on us. They smell fear and bad credit." "So you got a better idea? We need cash by Friday or this van becomes our permanent address." Molly sighed and folded the Evite into a paper airplane that immediately nosedived into the ashtray. "We could get actual jobs. Lisa literally offered us jobs at her party. She needs a clown." "That's our in! We're already hired. We just misinterpret the job description. Instead of bringing joy, we take it." "Fine. But if I have to wrestle a child for a Bluey plushie, I'm keeping the Bluey plushie. And we're not stealing the cake." Bill looked genuinely wounded at the idea of leaving cake behind. "We take the cake too. It's red velvet. That's my favorite." "We're not stealing a six-year-old's cake, Bill. There's a line. We crossed it, moved it, crossed it again, but cake is my new line." "Okay, okay, no cake. Just presents, quick in, quick out, and we never speak of this unless we get away with it." Molly turned the key. The van coughed, sneezed, and finally growled to life with the dignity of a shopping cart. "Then we will bring it up at every dinner party forever." "Let's go rob childhood." The clown noses on the dashboard stared back at them like judgmental cherries. "Wait, do we have to sing Happy Birthday? I can't sing." Bill popped a red nose on. It squeaked. "Don't sing. Just look remorseful in advance." Molly drove. "Also, if we see Bluey, grab Bluey." The van rolled forward.
created_at
"2026-07-25T17:41:15.205Z"
7/25/2026, 5:41:15 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
37197
moderation_latency
(null)
generation_time
40014
tokens_prompt
75
tokens_completion
734
native_tokens_prompt
225
native_tokens_completion
6985
native_tokens_completion_images
0
native_tokens_reasoning
6297
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
0.0299675
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f53bcd5ebf7e730046c6"
is_byok
false
latency
259
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-1785001275-vDFLFcpzoW72HJVyHINj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001275-j4pLOKdhVliGgSzljN0K"
upstream_id
"resp_6a64f53bcd5ebf7e730046c6"
total_cost
0.0299675
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
99.38%
Matches word count
n/a
neededClean
false
words
505
95.83%
Dialogue to Total Word Ratio
Ratio: 70.92%, Deviation: 0.92%
neededClean
false
wordsTotal
509
wordsDialogue
361
97.6017%