NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD6BCDTDBXQGKD32XHV87EX
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 70% dialogue
Duration:
28.7s
Cost:
$0.020749
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
94.99%
Dialogue to Total Word Ratio
(details)
97.1833%
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
Molly spread the crayon-drawn map across the hood of the getaway van. Bill stared at the house where six five-year-olds were screaming around a bouncy castle. "Okay, this is a new low, even for us." "Don't be dramatic, it's a high-value target," "High-value? It's Pokémon cards and slime kits!" "That limited edition Charizard is worth four hundred bucks on eBay, Bill. Four hundred." "From a seven-year-old named Timmy?" "Timothy. He goes by Timothy and he has a better portfolio than you." The van smelled faintly of greasepaint and stale birthday cake from their last reconnaissance mission. "You want us to infiltrate a children's birthday party dressed as what, exactly?" "Entertainers. You're Mr. Wiggles the clown, I'm Mrs. Sparkles the magician." "I am not wearing that nose again. Last time I got a rash." "Last time you ate the nose because you thought it was a cherry." "It was shiny and red and you said bring snacks!" Bill tugged at his red foam nose, which squeaked in protest every time he breathed too hard. "Focus. We go in at cake o'clock, during maximum distraction. While they sing happy birthday, we grab the present table and run." "Grab the present table? Molly, there are parents there. Moms. With eyes in the back of their heads." "Which is why you're doing the balloon animals. No mom suspects a man making a poodle." "What if they want something complicated? What if a kid wants a balloon giraffe?" Molly pulled a glittery top hat from a trash bag labeled DEFINITELY NOT STOLEN COSTUMES. "Then you make a giraffe. You're a professional thief, you can handle latex." "I can't even handle real animals. Remember the guard dog?" "Okay fine, what about you? What's the magician act?" "I'll be making the presents disappear. It's thematic." "That's cold, Molly. Cold. Stealing from kids." Outside, Timothy's mother was cutting a cake the size of a small car while dads filmed everything for evidence later. "We're not stealing from kids, we're redistributing joy from kids with too many toys to adults with gambling debts." "Exactly, so it's a victimless crime if you think about it selfishly." A dog wearing a party hat wandered past the fence and judged them silently. "We use it for extraction. We bounce out the back gate with the loot." "You want to bounce away with twenty wrapped presents while wearing clown shoes?" "No, I want you to bounce away while I drive. You were always the more aerodynamic one." The present table glittered under the patio umbrella, stacked impossibly high with ribbons that caught the afternoon sun. "You're majestic. Now put on the wig, Mr. Wiggles, we've got a birthday to ruin." "I hate that you make unethical decisions sound like team-building exercises." "And I love that you still show up. Ready?" The wind carried the sound of children chanting for sugar and chaos toward their guilty conscience. Bill sighed and picked up the giant squeaky hammer, already regretting everything.
created_at
"2026-07-25T17:49:43.745Z"
7/25/2026, 5:49:43 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
25773
moderation_latency
(null)
generation_time
28595
tokens_prompt
75
tokens_completion
746
native_tokens_prompt
225
native_tokens_completion
4816
native_tokens_completion_images
0
native_tokens_reasoning
4146
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
0.02074925
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f737cdba851dd5cf4d33"
is_byok
false
latency
226
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-1785001783-s7XgKiKqXYhp3UwY1fj7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001783-CbMfUA8G30l6ej0agtnj"
upstream_id
"resp_6a64f737cdba851dd5cf4d33"
total_cost
0.02074925
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
495
94.99%
Dialogue to Total Word Ratio
Ratio: 68.99%, Deviation: 1.01%
neededClean
false
wordsTotal
503
wordsDialogue
347
97.1833%