NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TB2WK8S1YXX8NR2JV2V83J
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
12.2s
Cost:
$0.038992
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 and Bill crouched behind Mrs Henderson's prize hedge, studying the birthday party unfolding beyond the garden fence with professional interest and jam sandwiches. Eight-year-old Timmy had received approximately forty presents, each wrapped in shiny paper that seemed to whisper temptingly toward their trembling, thieving fingers. Molly unfolded her crayon-drawn map, tapped the cake table twice, and whispered, "We grab presents during musical chairs, then flee through bouncy castle." Bill nodded solemnly while wearing a party hat he had found earlier, presumably for disguise, although it featured flashing lights and played music. He adjusted his oversized clown shoes and replied, "I will distract everyone by making suspicious balloon animals." Their plan required timing, courage, teamwork, several pillowcases, and absolutely no repeat of the unfortunate jelly incident from last summer's disastrous christening heist. Below them, inflatable dinosaurs wobbled, children shrieked happily, and one vigilant grandmother guarded the present table like a dragon protecting suspiciously rectangular treasure hoards. Molly checked her watch, counted backwards from ten, then remembered neither thief owned gloves, costumes beyond Bill's nonsense, or any plausible excuse whatsoever prepared. Nevertheless, grinning wickedly, they synchronized watches, stuffed sandwiches into pockets, and crept toward destiny, glory, and probably immediate capture shame.
created_at
"2026-10-13T09:56:46.835Z"
10/13/2026, 9:56:46 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2000
moderation_latency
(null)
generation_time
12177
tokens_prompt
75
tokens_completion
439
native_tokens_prompt
68
native_tokens_completion
1936
native_tokens_completion_images
0
native_tokens_reasoning
1584
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
0.038992
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885406-14z8XPCUzFYMtEASymTE"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885406-TKiwWiY0lttgKXa38fod"
upstream_id
"resp_6ace005f031f0a995998411c"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace005f031f0a995998411c"
is_byok
false
latency
710
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.038992
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: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%