NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K5PGS9488360GNP9ZHK7E5
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
14.6s
Cost:
$0.007926
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 Honeycutt's Bakery jingled as rain tapped the lace-curtained windows. The scent of cinnamon and butter hung thick in the warm air, despite the nearly empty display case. Only one cherry scone remained, sitting alone under the glass like a piece of evidence. "I suppose you've heard about Mayor Finch?" "That he cancelled the pie contest? Or that he was last seen arguing with you over that very scone?" "Both. And neither makes me look particularly innocent." "Well, you did tell half the town you'd poison anyone who tried to steal your recipe." "That was a joke. A poor one, I admit. Especially now that his slice is missing and he's missing too." "You don't think someone...?" "I think someone took more than the last scone. The police found crumbs on his office floor this morning. Sugar glaze. Same pink tint as this one." "So whoever was here left in a hurry." "Or wanted us to think they did." The oven timer dinged, but neither moved to check it. The kitchen door was ajar, and a fine trail of flour dust led toward the back alley. Outside, a police cruiser rolled slowly past the window, wipers squeaking against the rain. "That scone wasn't for the mayor, was it?" "No. It was for whoever comes back to finish what they started."
created_at
"2026-09-03T08:20:52.144Z"
9/3/2026, 8:20:52 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3387
moderation_latency
(null)
generation_time
14609
tokens_prompt
78
tokens_completion
400
native_tokens_prompt
68
native_tokens_completion
1845
native_tokens_completion_images
0
native_tokens_reasoning
1484
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
0.00792625
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788423652-ZCsK16kJ0mzCFJMUpu4q"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788423652-gZoS9WZIsrQjqtcBlAQz"
upstream_id
"resp_6a992de446b634b991aa4b0a"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992de446b634b991aa4b0a"
is_byok
false
latency
452
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.00792625
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)