NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBWVVBS8JSDBFZ0GQEG0C3
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
25.0s
Cost:
$0.055972
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 crouched behind a plastic flamingo in the suburban front yard, studying the birthday chaos through borrowed binoculars while balancing three empty gift bags. Bill arrived wearing a dinosaur costume two sizes too small, its tail knocking over lemonade, mailboxes, and one extremely suspicious garden gnome. Molly whispered, "We strike at noon and grab every single present." Bill adjusted his tiny foam claws and nodded gravely toward the inflatable castle bouncing with sugared children and questionable adult supervision. He replied, "Brilliant, unless the clown recognizes us from last Tuesday." Inside, a mountain of wrapped presents gleamed beside cupcakes, juice boxes, balloon animals, and a piƱata shaped like a suspiciously judgmental unicorn. Their plan involved confetti cannons, a borrowed stroller, fake mustaches, strategic snack distractions, and Molly performing an interpretive dance near the sprinkler controls. Bill had practiced crawling under laser ribbons tied between chairs, although the ribbons were merely streamers and mostly defeated him through static electricity. A seven year old general directed traffic with a bubble wand, assigning guards, inspecting invitations, and confiscating suspicious socks without mercy or hesitation. Molly grinned, produced two party hats, and placed one ceremoniously upon his lopsided dinosaur head. She added solemnly, "Then improvise."
created_at
"2026-10-13T10:10:58.037Z"
10/13/2026, 10:10:58 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2003
moderation_latency
(null)
generation_time
24674
tokens_prompt
75
tokens_completion
452
native_tokens_prompt
68
native_tokens_completion
2785
native_tokens_completion_images
0
native_tokens_reasoning
2408
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
0.055972
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886258-vVfYWs39DjnF0IAMe7se"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886258-mdfPplAlfC8NQBZ0NUse"
upstream_id
"resp_6ace03b29f56e1b1bfef4d30"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace03b29f56e1b1bfef4d30"
is_byok
false
latency
427
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.055972
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%