NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K4ZCP74M4HFPPQDYTW6HEH
Run Details
Model:
Muse Spark 1.3 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
52.3s
Cost:
$0.014055
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 200 word scene that has 10% 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 stolen birthday invitation across the hideout table while Bill studied the suburb map with intense criminal focus. "Let's crash that birthday party," Bill whispered. He circled the bouncy castle entrance in red marker and labeled all possible escape routes past the pony rides. "Bring big bags for presents," Molly grinned. Molly nodded wisely, remembering last year's disastrous retirement home bingo heist that ended with dentures in their getaway van. They needed disguises cheerful enough to fool suspicious mothers armed with juice boxes and sharp instincts for uninvited weirdos. "I'll distract clowns with cake," Bill added. Bill practiced his funny happy birthday smile in the cracked mirror, looking more like a constipated raccoon than cheerful entertainment. "You always fear small children," Molly laughed. Molly finalized the brilliant idiotic plan involving fake mustaches, a borrowed stroller for loot, and Bill pretending to be an overwhelmed magician with doves. Bill whimpered because doves pecked and children screamed louder than burglar alarms. They high-fived anyway, dreaming of Legos, dolls, and chocolate frosting eaten straight from stolen gift bags while hiding from angry parents. Tomorrow they would conquer glitter, chaos, and sugar-fueled toddlers for the greatest toy score ever attempted together bravely.
created_at
"2026-09-03T08:08:14.285Z"
9/3/2026, 8:08:14 AM
model
"meta/muse-spark-1.3-20260902"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
50860
moderation_latency
(null)
generation_time
52310
tokens_prompt
75
tokens_completion
339
native_tokens_prompt
68
native_tokens_completion
3287
native_tokens_completion_images
0
native_tokens_reasoning
3009
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
0.01405475
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422894-snwBoxph3bCPbvDevSfx"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422894-Sahe3Ndh6pjWclgMN3Sm"
upstream_id
"resp_6a992aee1162418643ef4419"
provider_responses
0
endpoint_id
"cf4f1b4e-1719-4b65-9111-7dd7635e5a2f"
id
"resp_6a992aee1162418643ef4419"
is_byok
false
latency
542
model_permaslug
"meta/muse-spark-1.3-20260902"
provider_name
"Meta"
status
200
total_cost
0.01405475
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
100.0000%