NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD4WF9FBMM53FDMZ9ZGCWC0
Run Details
Model:
Muse Spark 1.1 (Reasoning, Minimal)
Test:
Dialogue tags
Scenario:
Write 500 words with 50% dialogue
Duration:
20.2s
Cost:
$0.014821
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
90.6364%
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 laundromat table and weighted them with detergent bottles. Bill squinted. "This is a public park restroom map," Bill said. "No, this is the Johnsons' backyard," Molly said. "You just have to think fourth dimensionally." Bill leaned closer and knocked over a bottle of lavender Fabreze. Molly sighed and mopped it with Bill's sleeve. "Okay, walk me through it again," Bill said. "We are stealing birthday presents from a six-year-old?" "Seven-year-old," Molly corrected. "And it's not stealing, it's an aggressive repossession of unearned wealth. Do you know how many Paw Patrol trucks one child needs?" Bill stared. "Apparently twenty," Molly said. "And we are going to liberate them." The plan, as it existed, involved a clown costume, a collapsing cake, and what Molly called tactical distraction. "I still don't think I can fit in the clown costume," Bill said. "The pants are fighting me existentially." "That's because you put both legs in one hole," Molly said. "Fashion is not your strength, Bill. Felony is." Bill tugged at the rainbow wig that made his head look like a panicked traffic cone. "What if the kids recognize us?" Bill asked. "Last time Timmy bit me and I cried." "Timmy respects strength," Molly said. "This time you cry indoors. It's about branding." Molly pointed to a lopsided circle on the blueprint marked Bouncy Castle of Doom. "We enter during pin the tail," Molly whispered. "Maximum chaos, minimum adult supervision." Bill nodded solemnly, then ate a crayon. "Why did you eat a crayon?" Molly asked. "For camouflage," Bill said. "I want to blend in with the children." Molly closed her eyes for what witnesses would later describe as a prayer. "Focus," Molly said. "You will pose as the magician, make the rabbit disappear, then make the gift table disappear." "What rabbit?" Bill asked. "The one you bought," Molly said. "I bought a hamster," Bill said. "I named him Mr. Nibbles and he judges me." Molly pinched the bridge of her nose. "Fine, the hamster vanishes, you vanish, presents vanish," she said. "We meet at the getaway tricycle." Bill gasped with genuine admiration. "Molly, you're a genius," Bill said. "A cold, present-stealing genius." "Thank you," Molly said. "Now put on the clown shoes. And try not to squeak during the heist." Bill stood, wobbled, and immediately fell into a laundry cart full of socks. "This is perfect," he shouted from inside the cart. "I have established cover as laundry!" Molly looked at the map, at Bill, at the detergent bottles, and reconsidered every life choice that had led her here. "We are going to jail," Molly said. "Specifically children's jail." "Do they have juice boxes there?" Bill asked. "Probably," Molly said. Outside, a group of seven-year-olds practiced screaming, right on schedule. Bill emerged from the socks like a moth-eaten phoenix. "Let's go steal those Legos," he said. The automatic doors hissed open and cold February air rushed in. Bill's clown shoes squeaked once, twice, betraying everything. Molly grabbed his arm, grabbed the detergent, and marched into destiny wearing fury and fabric softener.
created_at
"2026-07-25T17:24:06.583Z"
7/25/2026, 5:24:06 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16811
moderation_latency
(null)
generation_time
20123
tokens_prompt
75
tokens_completion
826
native_tokens_prompt
225
native_tokens_completion
3421
native_tokens_completion_images
0
native_tokens_reasoning
2641
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
0.0148205
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f1369a789e6d46c047d5"
is_byok
false
latency
356
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-1785000246-GjJtB2TUyrTUQgeNR1HG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000246-vTz9jODTL2hyiqgcLxk8"
upstream_id
"resp_6a64f1369a789e6d46c047d5"
total_cost
0.0148205
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
81.27%
Matches word count
n/a
neededClean
false
words
512
100.00%
Dialogue to Total Word Ratio
Ratio: 50.00%, Deviation: 0.00%
neededClean
false
wordsTotal
520
wordsDialogue
260
90.6364%