NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ92MQ4DKQ8TYHFFACS3HXC
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.0s
Cost:
$0.004401
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 bell above the door chimed as the last customer shuffled out into the drizzly afternoon. The warm scent of cinnamon and brown butter hung in the air like a comfortable old blanket. "Did you hear about Franklin Marsh finding that lockbox under his floorboards?" "Everyone's heard. The question is what was *in* it." A tray of cooling scones slid onto the counter with a soft clatter. "Margaret at the post office says it was letters. Old ones, tied up with ribbon." "Margaret at the post office says a great many things." "She's right more often than not, you have to admit." The oven door swung open, releasing a fresh wave of warmth into the small shop. A silence settled between them, the comfortable kind that only comes with years of familiarity. "Franklin looked pale as my shortbread when he walked past this morning." "You were watching from the window again." "I was *checking the weather.*" A small laugh broke through. "Whatever was in that box, it's rattled him something fierce. Man's lived in that house forty years. Whatever's been sleeping under those floorboards has been sleeping a long time." "Until now."
created_at
"2026-02-18T02:25:51.265183+00:00"
2/18/2026, 2:25:51 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
606
moderation_latency
173
generation_time
6707
tokens_prompt
81
tokens_completion
305
native_tokens_prompt
77
native_tokens_completion
278
native_tokens_completion_images
(null)
native_tokens_reasoning
0
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
0.004401
router
(null)
provider_responses
0
id
"70ee4ba9-8859-464e-925c-e90d8100cea7"
status
200
is_byok
false
latency
606
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381543-FUCEldp19CzBSVS1jodZ"
upstream_id
"70ee4ba9-8859-464e-925c-e90d8100cea7"
total_cost
0.004401
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)