NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4Z7QKQFG66PE0QG4F2FF7
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
1m 57s
Cost:
$0.035377
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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 van smelled of stale fries and defeat as Molly spread the crayon map across the dashboard late Thursday night. Bill chewed a red balloon and stared at the suburban house circled three times in purple marker. Inside that living room a seven year old king would soon be buried in wrapping paper and glorious unguarded loot. Molly tapped the window with a plastic tiara and grinned like trouble wearing lipstick. Molly said, "We cannot just walk in wearing clown suits again." Rain drummed on the roof while Bill folded a lopsided party hat from a stolen parking ticket. Bill replied, "Why not It worked at the retirement home last spring." A dog barked down the street and a porch light flickered against wet pavement. Molly sighed, "Because kids remember clowns and parents call police faster." She pulled out binoculars shaped like juice cartons and watched balloons bob behind sheer curtains. Bill grinned, "Fine We dress as parents tired cranky holding juice boxes." He practiced his tired dad slouch and perfected a yawn that sounded almost convincingly exhausted. Molly nodded, "Better We bring a giant empty gift box and fill it slowly." Outside the van a minivan rolled past full of screaming kids waving foam swords and sticky hands. Bill whispered, "Genius Then we grab the LEGO pirates and the art sets." He sketched a crooked floor plan on a napkin marking the gift table beside the cake and the doorway. Molly warned, "No grabbing Everything must look calm and boring and normal." Thunder rumbled softly as she tucked glow sticks and trash bags into a diaper bag for cover. Bill bragged, "I am never boring I am festive and sneaky and fast." He blew up another balloon until it squeaked and tied it to the rearview mirror with flair. Molly laughed, "You ate three gift bows last time and cried during pinata." She tossed him a juice box and pointed at the neighbor houses dark and quiet and oblivious. Bill muttered, "The pinata hit back Molly It was self defense honestly." He slurped loudly then crushed the empty carton and shoved it into his jacket pocket. Molly ordered, "Just carry balloons look tired and whisper if anyone stares." A clown car drove by honking wildly and both thieves ducked low beneath the dashboard. Bill asked, "What about the birthday boy What if he recognizes us?" He peered through the foggy windshield at the bright banner flapping above the front door. Molly smiled, "Give him cake Distract with frosting and extra sprinkles always." She smeared frosting on his sleeve for authenticity and handed him extra napkins and confetti. Bill saluted, "Okay boss Operation Birthday Grab starts Saturday at noon." They bumped fists over the crayon map and listened to distant laughter drifting from nearby backyards full of evening chaos. Molly added, "And Bill shower first You smell like diesel." Bill started the van and they rolled toward Saturday dreaming of ribbons Legos and the perfect quiet getaway without any suspicion.
created_at
"2026-09-03T08:08:09.209Z"
9/3/2026, 8:08:09 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4764
moderation_latency
(null)
generation_time
116875
tokens_prompt
75
tokens_completion
759
native_tokens_prompt
68
native_tokens_completion
8304
native_tokens_completion_images
0
native_tokens_reasoning
7649
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
0.035377
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422889-Uc2DxMC4Jz53U04b4DAT"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422889-qv3WRVsEWl3G0YP11VDm"
upstream_id
"resp_6a992ae964cfe9bcd401423b"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992ae964cfe9bcd401423b"
is_byok
false
latency
640
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.035377
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Meta"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
500
100.00%
Dialogue to Total Word Ratio
Ratio: 30.00%, Deviation: 0.00%
neededClean
false
wordsTotal
500
wordsDialogue
150
100.0000%