NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYD501JXPQT0FFK5P0NMY8VH
Run Details
Model:
Muse Spark 1.1 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
20.6s
Cost:
$0.015037
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9997%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 like stolen frosting and bad decisions. Molly spread the blueprints across the dashboard, revealing Timmy's seventh birthday party. "Bill, you said bank job, not a bouncy castle infiltration." Bill adjusted his clown nose, which squeaked mournfully. "Listen, Molly, six-year-olds have zero security awareness and maximum present density. It's genius." "It's morally bankrupt. We're stealing from children." "We're liberating LEGO sets from ungrateful kids. Robin Hood would approve." "Robin Hood stole from the rich, not from Timmy." Molly sighed, folding the map where X marked the gift table. "So what's the plan, Bozo? Distract with balloon animals?" "Exactly! I make a giraffe, you grab the loot. Then we escape via the ball pit. Classic misdirection." Molly stared at him, deadpan. "You know I'm allergic to moral bankruptcy and latex." Bill grinned. "That's why you're wearing gloves. Trust me, this is our most mature heist yet." The bouncy castle wheezed outside like a guilty conscience. Molly considered the mountain of juice boxes waiting, sighed louder than the generator powering the castle, and finally muttered agreement despite every screaming instinct. Tomorrow she would definitely find a partner with standards lower than hers but higher than this. Very low bar indeed.
created_at
"2026-07-25T17:26:03.623Z"
7/25/2026, 5:26:03 PM
model
"meta/muse-spark-1.1-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
19232
moderation_latency
(null)
generation_time
20462
tokens_prompt
75
tokens_completion
341
native_tokens_prompt
225
native_tokens_completion
3472
native_tokens_completion_images
0
native_tokens_reasoning
3167
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
0.01503725
router
(null)
provider_responses
0
endpoint_id
"b2b9f6f9-8880-41c1-bd0c-867650fd5238"
id
"resp_6a64f1ac5113f82c04ae486f"
is_byok
false
latency
849
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-1785000363-ZEkV7WnRO9NayGa5hqlt"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1785000363-z1usYuL11u7c5OpsCZtR"
upstream_id
"resp_6a64f1ac5113f82c04ae486f"
total_cost
0.01503725
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: 50.50%, Deviation: 0.50%
neededClean
false
wordsTotal
202
wordsDialogue
102
99.9997%