NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV97CQBNTTB6X69P2DA2K3
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.4s
Cost:
$0.011110
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 jingled as Margaret swept inside, shaking rain from her umbrella. The smell of cinnamon and warm yeast wrapped around her like a wool blanket. "You're late. The scones are nearly gone." "I'm late because Harold Pennyworth is dead." A pause. Somewhere in the back, a timer dinged and went ignored. "Dead how?" "Dead in his garden, face down in the begonias. Constable Briggs is there now, pretending he knows what he's doing." "Poor Harold. He ordered a lemon tart just yesterday. Said it was for company." "Company? Harold hasn't had company since Nixon was president." "Well, he was quite insistent. Two forks, he said. I remember because he never asks for two of anything." "Two forks." "Two forks. And he paid in cash, which was odd, because he always ran a tab." "Margaret." "Hmm?" "Who picks up a lemon tart and pays cash the day before they fall dead in the begonias?" "Someone expecting to not be around to settle the tab." The timer dinged again. Neither woman moved toward the kitchen. Outside, the rain came harder, drumming against the window like impatient fingers asking to be let in.
created_at
"2026-04-24T13:36:18.339Z"
4/24/2026, 1:36:18 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
865
moderation_latency
(null)
generation_time
6307
tokens_prompt
81
tokens_completion
307
native_tokens_prompt
112
native_tokens_completion
422
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"
usage
0.01111
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"b003925c-7151-46e5-89b0-05a6256d1feb"
is_byok
false
latency
865
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777037778-CJiuQKsEjsnyjrF0XQXN"
session_id
(null)
api_type
"completions"
id
"gen-1777037778-lZo2IpZ5jYqMGlJbhVEZ"
upstream_id
"b003925c-7151-46e5-89b0-05a6256d1feb"
total_cost
0.01111
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)