NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-13-01M4TAYXZCNXY4JRKHXNKJFX06
Run Details
Model:
Muse Wonder (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
19.5s
Cost:
$0.047552
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
The bell over Butter & Crumb jingled at seven sharp, though the sign still read Closed. Flour hung in the morning air, sweet with cinnamon, vanilla, and something faintly burnt. “You're late, and you smell like a crime scene.” “I do not. That's lavender soap and poor life choices.” “Lavender doesn't usually come with police tape. In the pantry again?” “Not the pantry. By the ovens. Very dead, I'm afraid. And holding your rolling pin.” “My good rolling pin? The one with the loose handle?” “The very one. Your initials are carved right into it, clear as day.” “I carve them into everything. Once, even a pumpkin pie.” “That pie won the county fair. This is hardly the same. Please tell me nothing else was touched.” “Only the blueberry muffins. Stress eating isn't tampering.” “It is if the muffins were evidence.” “Then we have a problem, because I ate two. And the third is in my purse for later.” “We need to call someone.” “We need to frost something first. If word spreads before the church social, half of Maple Hollow will cancel their orders.” “And the other half will order extra, just for the gossip.” “Exactly. Now hand me the powdered sugar. If we're going down, we're going down beautifully.”
created_at
"2026-10-13T09:54:37.174Z"
10/13/2026, 9:54:37 AM
model
"meta/muse-wonder-20261012"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3052
moderation_latency
(null)
generation_time
19477
tokens_prompt
78
tokens_completion
413
native_tokens_prompt
68
native_tokens_completion
2364
native_tokens_completion_images
0
native_tokens_reasoning
2006
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
0.047552
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791885277-yURIDIGHZpnhKDlfyqH4"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791885277-xnP21g6n0ioG2y8ytJ5a"
upstream_id
"resp_6acdffdded83bd722748493d"
provider_responses
0
endpoint_id
"1232618d-ebfe-4338-9b68-d9127a57c8dd"
id
"resp_6acdffdded83bd722748493d"
is_byok
false
latency
881
model_permaslug
"meta/muse-wonder-20261012"
provider_name
"Meta"
status
200
total_cost
0.047552
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)