NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4T9VPGN1HE60QNEMR4M6JHX
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.5s
Cost:
$0.041472
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 birthday party floorplan across the kitchen table, weighing down its corners with teacups, a stapler, and one extremely suspicious garden gnome. Bill studied the drawing while eating frosting straight from the tub, nodding like a general preparing troops for glorious battle. Molly whispered, “We enter through the bouncy castle, grab everything, then vanish.” Bill replied, “Brilliant, except I get stuck in inflatable things every time.” She produced photographic evidence from three previous burglaries, each showing Bill wedged helplessly in chimneys, dog doors, laundry chutes, and one regrettably narrow grand piano. They therefore revised the route through the garden gate, past the magician, beneath the dessert table, and directly toward the towering pile of wrapped presents beside the piñata. Their disguises were flawless in theory: Molly would pose as a balloon artist, and Bill would squeeze into a dinosaur costume stolen from the neighboring recycling bin. They rehearsed tiptoeing over scattered toys, dodging suspicious grandparents, silencing squeaky shoes with marshmallows, and distracting the birthday child using an interpretive dance about tax season. At noon tomorrow, Operation Gift Snatch would begin, assuming Bill survived one final practice bounce without requiring butter, firefighters, or an industrial winch. Molly felt ready.
created_at
"2026-10-13T09:35:22.794Z"
10/13/2026, 9:35:22 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2275
moderation_latency
(null)
generation_time
12327
tokens_prompt
75
tokens_completion
425
native_tokens_prompt
68
native_tokens_completion
2060
native_tokens_completion_images
0
native_tokens_reasoning
1710
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
0.041472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791884122-wy3gpNQZ7PnQNXhGzwFQ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791884122-D2qU9ycJLM2YBEbe3taa"
upstream_id
"resp_6acdfb5b1681fac9e5a6427f"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6acdfb5b1681fac9e5a6427f"
is_byok
false
latency
793
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.041472
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: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
100.0000%