NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TBVVS2X013YXE2PSSEKZ2X
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.5s
Cost:
$0.033752
Provider:
Meta
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
"You smell that? Cinnamon, butter, and something suspiciously like smoke." "That is not smoke. Those are my cardamom buns, and they are supposed to be golden." "Golden is one thing. The fire alarm blinking is another." "Fine, one tray got a little enthusiastic. Now, did you come in to critique, or to tell me who took my recipe box?" "Maybe both. It was sitting on the counter yesterday, right next to the register?" "Yes, tied with blue ribbon. My grandmother's lemon bars, the mayor's favorite scones, all of it gone." "And this morning, Mrs. Peabody's bakery across town suddenly added lemon bars to her menu." "That woman has been after that recipe for twenty years. She once offered me fifty dollars and a knitted tea cozy." "Then why is her handwriting on the ransom note under your door?" "What ransom note?" "Twelve jars of your strawberry jam and nobody learns about the extra ingredient in your award-winning pie." "Oh, no. Not the pie secret." "So there is a secret. I knew it. What is it, a pinch of—" "If I tell you, you'll have to help me steal that box back tonight." "Deal. But we are taking the fresh buns. Breaking and entering requires snacks."
created_at
"2026-10-13T10:10:25.195Z"
10/13/2026, 10:10:25 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1895
moderation_latency
(null)
generation_time
10425
tokens_prompt
78
tokens_completion
356
native_tokens_prompt
68
native_tokens_completion
1674
native_tokens_completion_images
0
native_tokens_reasoning
1334
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
0.033752
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791886225-NjnKNFqRgKR2DwYLJYQ9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791886225-jQci7s7Qag2ECRWEiHBx"
upstream_id
"resp_6ace03911dcf10deed164130"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6ace03911dcf10deed164130"
is_byok
false
latency
432
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.033752
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%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)