NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD5SB5BYPQ90TVV37JNGMQ3
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
16.5s
Cost:
$0.011161
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
99.9605%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 and Bill crouched behind the bouncy castle. "Okay, Bill, we pose as entertainers, we walk in, we take every single present and we vanish." Bill frowned. "As entertainers? Molly, I hate kids. Last time I did balloon animals I got sued." "That kid wanted a realistic python, Bill. You gave him existential dread. Focus. The parents will be distracted by Pin the Tail." "And what about the clown they already hired? Huge guy, red nose, terrifying vibe?" "We tie him up in the pantry. Classic heist swap. You love pantry heists." "I love bank pantries, not cupcake pantries. What if they make us do magic?" "Then you do your disappearing coin trick where the coin actually disappears forever into your pocket. That's literally stealing, Bill. Your skillset." "Fine. But I want the LEGO set. For my nephew." "No. We fence everything. No feelings." "You're heartless, Molly." Molly grinned. "Relax, Bill, after this we can afford a real clown costume instead of your trash bag poncho." Bill sighed. "It's vintage, Molly, and it's breathable during high stakes toddler larceny." "Just remember the signal. If anyone yells cake, we grab the wagon and run." They bumped fists. "For the presents?" "For the presents."
created_at
"2026-07-25T17:39:52.625Z"
7/25/2026, 5:39:52 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15178
moderation_latency
(null)
generation_time
16442
tokens_prompt
75
tokens_completion
307
native_tokens_prompt
225
native_tokens_completion
2560
native_tokens_completion_images
0
native_tokens_reasoning
2261
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
0.01116125
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f4e8f8266c1c2abd4461"
is_byok
false
latency
281
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-1785001192-PUNU01OdEi8R51bVb7PX"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001192-6gNHB0pSKMiIiZzm2Elx"
upstream_id
"resp_6a64f4e8f8266c1c2abd4461"
total_cost
0.01116125
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
99.98%
Matches word count
n/a
neededClean
false
words
202
99.94%
Dialogue to Total Word Ratio
Ratio: 91.58%, Deviation: 1.58%
neededClean
false
wordsTotal
202
wordsDialogue
185
99.9605%