NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD611JVJ6RVJF6488A5RH39
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.9s
Cost:
$0.013915
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9989%
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 blueprint across the dashboard, revealing a crayon map of Timmy's backyard stolen magnetically from his refrigerator. Bill squinted at the glitter-covered entrance marked with stickers and a large X labeled presents. "Are we seriously stealing birthday presents from screaming six-year-olds?" Bill asked. "Absolutely, those limited edition Lego sets fund our tropical retirement plan." Molly replied. Their getaway driver was a bored teenager hired with pizza coupons and empty promises of adventure. The security system was reportedly a very angry mother armed with a spatula and unlimited juice boxes. Molly tapped the bouncy castle, which according to legend contained the mountain of loot and at least three capri-sun-related booby traps. Bill adjusted his clown disguise, which squeaked dangerously every time he breathed or considered retirement. The plan required infiltrating the magician's act, swapping the gift pile with empty boxes, and escaping via the sprinkler trench without getting soaked. Molly whispered the final step involved loudly crying until someone offered cake, a surprisingly effective distraction technique for hardened criminals. They nodded solemnly, bumped squeaky noses, and prepared to commit the most shameful felony of their entire ridiculous careers. Outside, children screamed with joy, completely unaware of impending present-related doom.
created_at
"2026-07-25T17:44:04.965Z"
7/25/2026, 5:44:04 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17709
moderation_latency
(null)
generation_time
18790
tokens_prompt
75
tokens_completion
349
native_tokens_prompt
225
native_tokens_completion
3208
native_tokens_completion_images
0
native_tokens_reasoning
2939
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
0.01391525
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f5e5f891cd3cc99f4ce2"
is_byok
false
latency
232
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-1785001444-VMWwgrBvS5A98ibKSUmV"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785001444-GdTaQYdigti8IzVEGYUe"
upstream_id
"resp_6a64f5e5f891cd3cc99f4ce2"
total_cost
0.01391525
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
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 10.68%, Deviation: 0.68%
neededClean
false
wordsTotal
206
wordsDialogue
22
99.9989%