NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K58M9XT4TYKHFYJF5ACZDF
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 500 words with 30% dialogue
Duration:
50.9s
Cost:
$0.042147
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.84%
Dialogue to Total Word Ratio
(details)
99.9200%
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 community center on Maple Street had never been designed to withstand a professional heist. Its front doors were glass, its alarm system was a bell that jingled when you entered, and its most formidable security feature was a bored teenager at the reception desk named Kevin. For Molly and Bill, who had once tunneled into a bank vault using only soup spoons and misplaced confidence, this was practically an invitation. Molly crouched behind the low brick wall that bordered the parking lot, binoculars pressed to her eyes, watching the steady stream of minivans unload. Each child emerged clutching a brightly wrapped present, vanishing into the building where balloons strained against the ceiling. "That's seventeen," Molly whispered. "Seventeen presents, plus cake," Bill murmured, checking his clipboard. The clipboard held a hand-drawn map, three expired coupons, and a juice box that had already leaked. "We are not stealing cake, Bill." "But it's ice cream cake," Bill said. Molly lowered the binoculars and stared at the puppet stage where the presents were stacked in a glittering tower while a clown twisted balloons. "Focus. The parents are distracted. When they sing, we move," Molly said. "Classic misdirection," Bill nodded. "You will enter as the backup clown and grab the tablecloth," Molly instructed. Bill stared at the duffel bag containing one red nose, two oversized shoes, and a rubber chicken that squeaked despairingly. "I thought we agreed I don't do clown anymore," Bill muttered. "That was you stuck in a tiny car for three hours," Molly replied. "Is it really different?" Bill asked. Molly zipped the bag shut. "Listen, you do five minutes of slapstick, grab the presents, and we run to the getaway stroller," she said. "We have a getaway stroller?" Bill asked. "It's motorized. I upgraded it," Molly answered. From inside, the faint off-key chorus of happy birthday began to warble through the glass doors. "That's our cue. Act natural," Molly whispered. Bill affixed the red nose, which immediately fell off, sighed, picked it up, and waddled toward the side entrance as parents clapped arrhythmically inside. Molly followed, dragging the empty stroller, already calculating how many gift receipts they would need to fence seventeen plastic dinosaurs and glitter-covered craft kits. "Remember, children love clowns," Bill whispered, trying to sound confident. "They love terrified clowns even more," Molly said dryly. The clown inside finished a balloon giraffe, the lights dimmed slightly, and the scent of frosting and juice boxes drifted into the parking lot. "Just smile, trip, and pull," Molly ordered. "Smile, trip, pull. Got it," Bill repeated. "And don't eat the cake until we're outside," Molly added as Bill opened the door. The birthday song grew louder, children screaming the lyrics, parents filming, and Kevin the teenager still scrolling on his phone, oblivious. "This is either brilliant or deeply embarrassing," Bill muttered. "With us, it's always both," Molly grinned. They slipped inside together, ready to steal joy itself. "We are definitely getting extra cake after this, right? Absolutely double extra cake please."
created_at
"2026-09-03T08:13:16.996Z"
9/3/2026, 8:13:16 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3099
moderation_latency
(null)
generation_time
50861
tokens_prompt
75
tokens_completion
862
native_tokens_prompt
68
native_tokens_completion
9897
native_tokens_completion_images
0
native_tokens_reasoning
9148
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
0.04214725
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423196-F0ye9Kh5osjB3NlK7cKU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423196-UI6xOPLNeqxTQ3aD0tCO"
upstream_id
"resp_6a992c1d3c766cb36e7e4e33"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992c1d3c766cb36e7e4e33"
is_byok
false
latency
289
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.04214725
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
99.84%
Dialogue to Total Word Ratio
Ratio: 29.82%, Deviation: 0.18%
neededClean
false
wordsTotal
503
wordsDialogue
150
99.9200%