NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TB60ZKF549KSK5D9M6CQ7P
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
15.3s
Cost:
$0.054472
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 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
Molly perched on the fire escape, peering through binoculars at the balloon-festooned garden below, where sugar-hyped children screamed like tiny alarms. "Tell me again why adults are not invited," Bill whispered. He adjusted his clown wig, which kept sliding over one eye, ruining his menacing aura completely. "Because, genius, we are crashing it disguised as entertainment, remember?" Molly hissed. She pointed toward the gift table, a glittering mountain of wrapped boxes guarded by one formidable grandmother and several juice boxes. "That granny has elbows like weapons," Bill muttered nervously. "Relax. You juggle, I sing, everyone looks away, then we swap the presents for decoy boxes filled with socks." Below, the birthday boy attempted to eat his own party hat while parents applauded encouragingly. "What if they request actual balloon animals?" he asked, panicking slightly. "Then improvise. Everything vaguely sausage-shaped counts as a dog." She stuffed empty sacks beneath her sparkly magician's cape. "I feel morally weird stealing from an eight-year-old." Bill admitted. "He has forty presents, Bill. Forty. Even Santa thinks that is excessive profiteering." Molly grinned wickedly. "Fine. Operation Pinata begins in three, two..." "Wait, do clowns knock, or do we just honk ominously?" Bill replied. "Honk twice, obviously."
created_at
"2026-10-13T09:58:29.628Z"
10/13/2026, 9:58:29 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2589
moderation_latency
(null)
generation_time
15317
tokens_prompt
75
tokens_completion
427
native_tokens_prompt
68
native_tokens_completion
2710
native_tokens_completion_images
0
native_tokens_reasoning
2321
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
0.054472
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885509-GSrXISWlqld2Risxhbup"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885509-Npgmdp32iu0z2V0PBKQS"
upstream_id
"resp_6ace00c68a5c0c05780440cf"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace00c68a5c0c05780440cf"
is_byok
false
latency
1058
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.054472
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: 50.24%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
103
100.0000%