NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTW0M57H6R9Y7F21JXX19A
Run Details
Model:
Claude Opus 4.7
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
6.9s
Cost:
$0.011375
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
80.15%
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 the cobblestones outside Ravenscroft Manor as Detective Miles Harrow stepped from his car into the howling October night. The front door stood ajar, spilling amber light across the wet stone steps where a single black glove lay abandoned. Inside, the butler waited with trembling hands, his silver tray forgotten on a table beside an overturned crystal wine decanter. "He's in the library, sir," the old man whispered, eyes darting toward the staircase as thunder rattled the tall leaded windows. Harrow followed the narrow corridor past oil paintings whose painted eyes seemed to track his slow, deliberate progress through the shadows. Lord Ashworth sat slumped behind his mahogany desk, a jeweled letter opener buried deep within his starched white dress shirt. Blood had pooled across an unfinished letter, staining the words until only one legible phrase remained: "I know your secret." Three guests huddled near the fireplace, each clutching a drink, each wearing expressions that blended genuine shock with something far uglier. Harrow removed his damp hat, surveyed the room carefully, and noted that every single window had been locked from inside. "Nobody leaves this house tonight," he announced quietly, and somewhere upstairs, a floorboard creaked beneath the weight of hidden footsteps.
created_at
"2026-04-24T13:29:05.426Z"
4/24/2026, 1:29:05 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1865
moderation_latency
(null)
generation_time
6804
tokens_prompt
46
tokens_completion
329
native_tokens_prompt
65
native_tokens_completion
442
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
0.011375
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"c2df8b0d-4a42-4f25-b0f4-fd78b4df0c74"
is_byok
false
latency
1865
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-1777037345-bn6L3gOavRYpSGEILgIl"
session_id
(null)
api_type
"completions"
id
"gen-1777037345-2fPJ0Ofs9YBYGgf3MHRW"
upstream_id
"c2df8b0d-4a42-4f25-b0f4-fd78b4df0c74"
total_cost
0.011375
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
80.15%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
20
3
21
4
21
5
20
6
41
7
20
8
20