NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8VPC4D73ENBKW7HE96RES5
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.0s
Cost:
$0.008970
Provider:
Amazon Bedrock
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 morning light filtered through the front windows of Sweet Crumb Bakery, catching the flour dust that always seemed to hang in the air like tiny constellations. Behind the counter, a tray of cinnamon rolls sat cooling, their glaze still glistening. "You heard about Margaret's garden shed, I assume." "Heard about it? I drove past it this morning. Police tape everywhere." "Three weeks now since anyone's seen her cat, and suddenly they find that locked trunk buried under her begonias." "I don't want to speculate." "Then why are you whispering?" A pause filled the space between them, punctuated only by the soft ticking of the rooster clock above the register. "All I'm saying is, I delivered a dozen scones to her house last Tuesday, and someone had dug up the entire north side of the yard. Freshly turned soil. And Margaret stood in the doorway looking like she hadn't slept in days." "That woman has always been peculiar." "Peculiar is collecting porcelain frogs. This is something else entirely." The bell above the door chimed. Both women straightened, smiles appearing like masks pulled from a drawer. "Welcome to Sweet Crumb. What can we get you, Sheriff?"
created_at
"2026-02-24T22:18:09.939Z"
2/24/2026, 10:18:09 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1420
moderation_latency
125
generation_time
9785
tokens_prompt
81
tokens_completion
348
native_tokens_prompt
94
native_tokens_completion
340
native_tokens_completion_images
(null)
native_tokens_reasoning
34
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00897
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"81f14e1a-b7b7-4cf0-aa26-b911fc6d5628"
is_byok
false
latency
1381
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771971489-vAnrKD21z7oaqnEYwz7l"
upstream_id
"81f14e1a-b7b7-4cf0-aa26-b911fc6d5628"
total_cost
0.00897
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)