NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA1J0YXRTC9RJV2WKQ2TAH
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
10.3s
Cost:
$0.004564
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 smell of cinnamon still clung to the walls of Higgins' Bakery, though the ovens had gone cold hours ago. Maple Hollow's morning light slanted through the front window, catching dust motes above the empty display case. "You're telling me Dot Higgins didn't bake a single thing yesterday? In forty years, that's never happened." "Not one scone. I called at six, no answer. Called again at seven. Nothing." "And the back door was unlocked?" "Wide open. Flour bag tipped over on the counter, like she just walked away mid-recipe." "Did you check the register?" "Empty. But not robbed-empty. Careful-empty. Like someone counted it out." "That's odd. Dot never lets anyone touch that register but her." "Exactly what I thought. And there's this—" A small brass button, tarnished at the edges, was set on the counter between them. "That's not from anything Dot wears." "No. It's from a police uniform. I checked." "You think Officer Reilly was here?" "I think somebody wanted us to think he was." "So where's Dot?" "That's what worries me. If someone's trying to frame Reilly, they needed Dot gone first. And gone quietly." "Then we'd better find her before whoever did this decides quiet isn't enough."
created_at
"2026-07-01T07:42:06.89Z"
7/1/2026, 7:42:06 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3293
moderation_latency
(null)
generation_time
10272
tokens_prompt
81
tokens_completion
327
native_tokens_prompt
107
native_tokens_completion
435
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"end_turn"
service_tier
"default"
usage
0.004564
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01BwPvz7ZaNUFRRTgyDcUXvo"
is_byok
false
latency
3206
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782891726-XYeVEW43w9qhAEz8G9om"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891726-ens06BBV7GEL6RxotSuK"
upstream_id
"msg_01BwPvz7ZaNUFRRTgyDcUXvo"
total_cost
0.004564
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)