NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ9508XMNK0ZX0PPZ05VQNB
Run Details
Model:
Claude Sonnet 4.6
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.9s
Cost:
$0.004386
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 left, leaving the warm, flour-dusted bakery in comfortable quiet. The smell of cinnamon rolls still hung in the air like a sweet promise. "You heard about Gerald Finch, I suppose." "Found him in his greenhouse this morning, they say. Surrounded by all those prize-winning tomatoes." A tray slid onto the cooling rack with a soft clatter. "Margaret at the post office says it wasn't natural causes." "Margaret at the post office says a great many things." "She's right more often than not, though." The sound of a butter knife scraping across fresh bread filled the brief silence. "His nephew was in here yesterday. Bought six of those lemon tarts Gerald always hated." "That's an odd detail to remember." "I remember everything that happens in this bakery. You'd be surprised what people reveal when they're standing in front of a pastry case." "And what did the nephew reveal?" A pause, deliberate and weighted, followed by the soft thud of dough being set on the counter. "That he already knew he'd be the one inheriting that greenhouse. Gerald hadn't told a soul yet."
created_at
"2026-02-18T02:27:08.707051+00:00"
2/18/2026, 2:27:08 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
509
moderation_latency
118
generation_time
6764
tokens_prompt
81
tokens_completion
304
native_tokens_prompt
77
native_tokens_completion
277
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
0.004386
router
(null)
provider_responses
0
id
"6e63c0bd-0e2a-4777-957b-136d3f16f28d"
status
200
is_byok
false
latency
508
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381621-HnXG5HONiiBGSwGwWRPc"
upstream_id
"6e63c0bd-0e2a-4777-957b-136d3f16f28d"
total_cost
0.004386
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)