NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WVPT230EHBV6J22PT209C
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
9.8s
Cost:
$0.009070
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 light filtered through the checkered curtains of Sweet Crumb Bakery, casting warm squares across the flour-dusted counter. The scent of cinnamon rolls hung thick in the air, mingling with fresh coffee and something darker — suspicion. "You heard about Margaret's garden shed, I suppose." "Heard about it? I drove past it this morning. Police tape everywhere. Looked like something out of a television program." "They found Walter Briggs's missing ledger in there. Tucked right behind a bag of potting soil." "Margaret wouldn't steal a ledger. She can barely remember where she puts her reading glasses." "That's exactly what someone *wants* us to think." A tray of scones emerged from the oven, golden and perfect. One was plated and slid across the counter without a word of transaction — just the quiet understanding of regulars. "I saw someone near that shed Tuesday night. Tall. Wearing that awful green coat from the thrift shop on Pine Street." "Half the town owns that coat." "Not half the town was out walking at midnight." The coffee maker gurgled into the silence. Outside, a crow landed on the bakery's window box and tilted its head, as if listening. "I think we need to talk to Dorothy."
created_at
"2026-02-24T22:38:33.29Z"
2/24/2026, 10:38:33 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1597
moderation_latency
212
generation_time
9527
tokens_prompt
81
tokens_completion
359
native_tokens_prompt
94
native_tokens_completion
344
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
0.00907
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"e54473c9-1fa0-4457-aaa6-c5407849af87"
is_byok
false
latency
1507
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972713-LvjWJMixSGkcCbyR8ZU3"
upstream_id
"e54473c9-1fa0-4457-aaa6-c5407849af87"
total_cost
0.00907
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)