NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTXCKZ5T4A7Y98T0VC7SXK
Run Details
Model:
Claude Opus 4.7
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
6.2s
Cost:
$0.008625
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
65.57%
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 slate roof of Blackwood Manor as Inspector Hollis stepped from his car into the gathering October gloom. The front door yawned open before he reached it, revealing a pale butler whose trembling hands betrayed recent horror. Inside, candles flickered against mahogany walls, casting restless shadows across portraits of ancestors who seemed to watch him accusingly. Six guests huddled together in the drawing room, their evening clothes rumpled, their faces drained of every possible color. Lord Ashworth lay sprawled beside the fireplace, a silver letter opener buried precisely between his third and fourth ribs. No one had heard anything unusual, they claimed, though dinner had ended scarcely forty minutes before the grim discovery. Hollis removed his wet coat slowly, studying each suspect in turn while the grandfather clock struck eleven hollow times. Someone in this elegant room had committed murder, and someone, he suspected, would very soon attempt to commit another.
created_at
"2026-04-24T13:29:50.476Z"
4/24/2026, 1:29:50 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1015
moderation_latency
(null)
generation_time
6127
tokens_prompt
46
tokens_completion
250
native_tokens_prompt
65
native_tokens_completion
332
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
0.008625
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"11e7a7e0-f3c9-4e2e-9e38-6ae14dc02883"
is_byok
false
latency
1008
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-1777037390-9uYWF3bmcGC87ldtAEUa"
session_id
(null)
api_type
"completions"
id
"gen-1777037390-u3LInY2D7AKLqUdkpGU6"
upstream_id
"11e7a7e0-f3c9-4e2e-9e38-6ae14dc02883"
total_cost
0.008625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
65.57%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
19
2
19
3
19
4
19
5
19
6
19
7
19