NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WP0GMC4RW624AP6ZYMP5G
Run Details
Model:
Claude Sonnet 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
8.5s
Cost:
$0.005457
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 rush had thinned to a quiet trickle when the bell above the door chimed. The smell of cinnamon rolls and fresh coffee hung in the warm air like a comfortable secret. "Did you hear about Gerald Fitch? Found his back door wide open this morning, till cleaned right out." "No." A coffee mug clinked against the counter. "How much?" "Enough to ruin a man's Monday. Third shop on Maple this month, you know." "I know. I've been keeping count." Flour-dusted hands slid a bag of sourdough across the glass case. "Sheriff Danby still thinks it's teenagers." "Sheriff Danby thinks everything is teenagers." A small laugh softened the tension. Outside, a sparrow landed on the windowsill and tilted its head as if listening. "My cousin says she saw headlights behind the hardware store last Tuesday, around two in the morning. Didn't think much of it then." "She should tell someone." "That's what I said." The register drawer opened and closed with a soft ring. "Here's your change. And listen — maybe don't leave the back propped open when you're taking deliveries anymore. Just until things settle." "Yeah." A pause. "Yeah, you're probably right."
created_at
"2026-02-24T22:35:26.62Z"
2/24/2026, 10:35:26 PM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
862
moderation_latency
226
generation_time
8152
tokens_prompt
81
tokens_completion
343
native_tokens_prompt
94
native_tokens_completion
345
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
0.005457
router
(null)
provider_responses
0
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
id
"c1b7cca3-1771-4782-bf4c-1101a1a2ad0a"
is_byok
false
latency
860
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972526-SYDxvHx2mfD3ZwqCmXKt"
upstream_id
"c1b7cca3-1771-4782-bf4c-1101a1a2ad0a"
total_cost
0.005457
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)