NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8TR78JVJRKHHGPMP0MJ1TE
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.2s
Cost:
$0.005382
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
60.65%
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 smell of cinnamon rolls drifted through the warm air as the little bell above the door chimed. Flour dusted the wooden countertops, and a glass case displayed neat rows of scones and fruit tarts. Outside, the main street of Millhaven sat quiet in the early morning grey. "You heard about Gerald Finch, I suppose." "Found him in his greenhouse, they're saying. Door locked from the inside." "That's what's strange about it." A tray slid into the oven with a soft clang. "Gerald never locked anything. Left his car running in the driveway half the time." "His sister telephoned me last night. Beside herself, poor thing." "Can't blame her."
A dish towel snapped
against the counter. "You want the usual? I've got fresh blueberry this morning." "Please. Do the police have anyone in mind?" "Deputy Marsh was in here at six asking questions. Wanted to know if Gerald had been acting peculiar lately." "And had he?" A long pause settled between them, filled only by the tick of the wall clock and the gentle hiss of the oven. "He bought two dozen black walnut cookies last Tuesday. Said they weren't for him." "That is peculiar."
created_at
"2026-02-24T22:01:41.914Z"
2/24/2026, 10:01:41 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
835
moderation_latency
136
generation_time
8006
tokens_prompt
81
tokens_completion
335
native_tokens_prompt
94
native_tokens_completion
340
native_tokens_completion_images
(null)
native_tokens_reasoning
33
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
0.005382
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"681b3729-8dc0-4a90-accc-5125d964d53b"
is_byok
false
latency
835
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771970501-yHj3KRYOzZ1ylBypJHNh"
upstream_id
"681b3729-8dc0-4a90-accc-5125d964d53b"
total_cost
0.005382
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
60.65%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"A dish towel snapped"