NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZVA7WDKJZ2YFTVREAXAF5H
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.8s
Cost:
$0.010810
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 in, clutching her handbag like a shield. Flour dust motes danced in the morning light, and the smell of cinnamon wrapped around her like a shawl. "You've heard, then." "Heard? The whole town's heard. Edna Pritchard doesn't lose a prize-winning rosebush without making sure of it." "She thinks it was Harold." "Harold can barely bend down to tie his shoes, let alone dig up a rosebush in the dead of night." "That's what I said. But you know Edna." A pause, filled with the soft thump of dough against the marble counter. "Two scones or three today?" "Three. And a cruller, if you've got one left." "For you, always." "The odd thing is, I saw Marcus Bell walking past her garden Tuesday evening. Carrying a shovel." The kneading stopped. "A shovel?" "A shovel. And he had that look about him—you know the one." "The look he had before the business with the mailboxes?" "Precisely that look." "Well. That changes things, doesn't it?" "I rather thought it might. Another coffee, while we think it over?" "Pour two. This is going to take some considering."
created_at
"2026-04-24T13:36:51.61Z"
4/24/2026, 1:36:51 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
702
moderation_latency
(null)
generation_time
7658
tokens_prompt
81
tokens_completion
308
native_tokens_prompt
112
native_tokens_completion
410
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
0.01081
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"3700a412-a5e3-497e-8266-51ec8ecd9e5e"
is_byok
false
latency
702
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-1777037811-SyjLkBja8APrnWwkI13i"
session_id
(null)
api_type
"completions"
id
"gen-1777037811-m90OJX4wPYL4xrC26iz0"
upstream_id
"3700a412-a5e3-497e-8266-51ec8ecd9e5e"
total_cost
0.01081
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)