NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1K50TCK98F6AR28SE6QRD41
Run Details
Model:
Muse Spark 1.2 (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
20.8s
Cost:
$0.010778
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 bakery on Main smelled like butter and cinnamon, warm against the October chill outside. Sun through the front window lit the empty cake stand in the center of the glass case, a perfect circle of crumbs left behind. The back door was still locked, the front door's bell had not yet rung. "You're here before the timer. That's new." "So is an empty pedestal where the apple crumble was supposed to be for the harvest contest." "Gone? I left it cooling by the window last night." "And the window was open a crack this morning. Just enough for cold air. And hands." "There's powdered sugar on the sill. And a trail to the register." "But nothing taken from the till. Only the crumble. Who steals a single contest pie and leaves the cash?" "Someone who wanted to make sure you didn't win on Saturday. Someone who knew you'd use your grandmother's recipe." "Then they left a clue. Look, a button, caught on the sill. Navy blue, brass anchor." "That looks awfully familiar." Outside, Main Street was waking up, but inside the bakery the air had gone cold with something more than October.
created_at
"2026-09-03T08:09:01.081Z"
9/3/2026, 8:09:01 AM
model
"meta/muse-spark-1.2-20260805"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2810
moderation_latency
(null)
generation_time
20741
tokens_prompt
78
tokens_completion
318
native_tokens_prompt
68
native_tokens_completion
2516
native_tokens_completion_images
0
native_tokens_reasoning
2230
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
0.010778
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788422941-gL3mMcVXSHvKCbyGMbmY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788422941-VAYbQAi0GjDlQy2hYVrU"
upstream_id
"resp_6a992b1d6095b61d4a6a498f"
provider_responses
0
endpoint_id
"ffc8e76e-808a-44d2-bd21-c6ac16e721cb"
id
"resp_6a992b1d6095b61d4a6a498f"
is_byok
false
latency
1280
model_permaslug
"meta/muse-spark-1.2-20260805"
provider_name
"Meta"
status
200
total_cost
0.010778
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)