NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRH24RVQHJ7C99BS0STSXX
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
11.2s
Cost:
$0.013410
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 over the door jangled, and a gust of November air rolled across the cooling racks. "You're out of the cinnamon twists already. It's barely eight." "Marjorie Pike bought the whole tray. Said she needed them for the church raffle." "There is no church raffle until spring." A pause. Somewhere in the back, an oven timer ticked toward zero. "That's what I thought. And she paid in exact change, which she has never once done in eleven years. Always a twenty, always wants the coins back for the meter." "So she planned it. She knew exactly what she was buying and what it cost." "Or somebody told her." Flour hissed onto the marble slab. A rolling pin took up its slow, thoughtful rhythm. "Did she mention Harold?" "Not a word. That's the strange part. Three weeks that man's been missing from the historical society and she didn't say his name once. Usually she can't get through a doughnut without complaining about him." "People go quiet about the things that frighten them." "People go quiet when they've got something in their handbag they don't want you seeing." "And did she?" "A key. Brass, old, tied with green ribbon. It was on the counter for half a second before she snatched it back."
created_at
"2026-07-25T13:48:09.76Z"
7/25/2026, 1:48:09 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3667
moderation_latency
(null)
generation_time
11103
tokens_prompt
78
tokens_completion
418
native_tokens_prompt
107
native_tokens_completion
515
native_tokens_completion_images
(null)
native_tokens_reasoning
106
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
0.01341
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt2jUrknipEb4SjWUA5"
is_byok
false
latency
1478
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784987289-Xw6bc8sFPeoDkO47Y47N"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987289-E6KuIqCvXBmNi23KwTcH"
upstream_id
"msg_011CdNt2jUrknipEb4SjWUA5"
total_cost
0.01341
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)