NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GB5WK3Q1B1FG6DWN6959V
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
6.8s
Cost:
$0.010360
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 shook rain from her umbrella, the scent of cinnamon and yeast wrapping around her like a warm shawl. "You're late. I saved you the last cruller, but only just." "Bless you. I would have wrestled someone for it." "Wrestled? You? In that cardigan?" "Don't underestimate a woman who's been to three council meetings this week." A pause, the clink of a cup settling onto a saucer. "You heard about Harold, then." "Heard? I found the poor man. Face down in his prize-winning marrow, if you can believe it." "I can't. Harold wouldn't leave that marrow unattended for the Queen herself." "Exactly what I said to Constable Briggs. And do you know what he told me?" "What?" "That I should leave the thinking to the professionals. The professionals, Edith. The man still can't spell 'suspicious' without asking." "So what are we going to do about it?" "We? I only came in for a cruller." "And yet here you are, telling me everything. Sit down. I'll put the kettle on properly. Now—start from the beginning, and don't leave out the marrow."
created_at
"2026-04-24T19:44:22.423Z"
4/24/2026, 7:44:22 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
680
moderation_latency
(null)
generation_time
6694
tokens_prompt
81
tokens_completion
294
native_tokens_prompt
112
native_tokens_completion
392
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
0.01036
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"aceef4c2-b2ca-487a-861c-2607dbbd212c"
is_byok
false
latency
679
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-1777059862-61GSRI0Xs4buZL5vrEhB"
session_id
(null)
api_type
"completions"
id
"gen-1777059862-WqLnweoz65YkF4ZhYoTe"
upstream_id
"aceef4c2-b2ca-487a-861c-2607dbbd212c"
total_cost
0.01036
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)