NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G01CX1WG8219CPXVH9SC6
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
17.7s
Cost:
$0.071575
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
83.33%
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
The rain hammered against the cracked windows of Ashford Manor as Detective Miriam Cole stepped carefully across the creaking threshold. A single lamp flickered beside the body, casting long, trembling shadows across the old oak floor and stained silk rug. Lord Ashford lay sprawled before the cold stone hearth, one pale hand clutching a torn letter sealed with crimson wax. Detective Miriam knelt down slowly, her gloved fingers hovering above the fatal wound, her sharp eyes cataloguing every suspicious detail. Behind her, the elderly butler cleared his throat nervously, his trembling voice barely audible over the howling winter storm outside. "Everyone in the household was present tonight, Detective, and every single one of them had a reason to despise him." Miriam rose slowly, tucking her notebook away, knowing that before dawn arrived, a killer would be hiding among these guests.
created_at
"2026-04-24T19:38:17.502Z"
4/24/2026, 7:38:17 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2370
moderation_latency
(null)
generation_time
17414
tokens_prompt
46
tokens_completion
469
native_tokens_prompt
65
native_tokens_completion
2850
native_tokens_completion_images
(null)
native_tokens_reasoning
245
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
0.071575
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"4bddb2e5-1ddc-4ef7-ba3b-88ff1d367921"
is_byok
false
latency
728
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-1777059497-VfFijT8rRVNXXA09AVU8"
session_id
(null)
api_type
"completions"
id
"gen-1777059497-Q73HXgsIoUuW6jg68Rod"
upstream_id
"4bddb2e5-1ddc-4ef7-ba3b-88ff1d367921"
total_cost
0.071575
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
83.33%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
20
2
20
3
20
4
20
5
40