NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV1Q9Q9SZQPA24B2B9ZAB0
Run Details
Model:
Claude Opus 4.7
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
6.2s
Cost:
$0.010075
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
76.41%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain hammered against the bay windows of Blackwood Manor, drowning the distant church bells that tolled midnight across the moors. Inspector Harriet Cole stepped carefully over the threshold, her boots leaving wet prints on the polished oak entrance floor. The butler stood trembling beside an overturned candelabra, wax pooling like blood across the Persian rug beneath him. Seven guests huddled silently in the drawing room, their faces pale masks reflecting the dying embers of the stone fireplace. Lord Ashworth lay sprawled across his mahogany desk upstairs, a silver letter opener protruding from between his stiffened shoulder blades. Harriet examined the scene quietly, noting the open window, the scattered papers, and one peculiar detail nobody had mentioned yet. A single white rose rested carefully on the victim's chest, its thorns stripped clean and stem wrapped in black ribbon. She turned slowly toward the doorway where the guests had gathered, studying each trembling face with practiced, unflinching, deliberate attention. Someone inside this house had committed murder tonight, and every person present knew far more than they were currently willing to admit.
created_at
"2026-04-24T13:32:12.483Z"
4/24/2026, 1:32:12 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2163
moderation_latency
(null)
generation_time
6117
tokens_prompt
46
tokens_completion
295
native_tokens_prompt
65
native_tokens_completion
390
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
0.010075
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"f45eb401-aff4-4bc0-a0db-9cf62069ead9"
is_byok
false
latency
2160
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-1777037532-JmNi0MOhmzZJnXbk1D4f"
session_id
(null)
api_type
"completions"
id
"gen-1777037532-eygkFjDuDTQRmiuGAakm"
upstream_id
"f45eb401-aff4-4bc0-a0db-9cf62069ead9"
total_cost
0.010075
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
76.41%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
19
2
18
3
20
4
20
5
20
6
20
7
20
8
22