NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV1J8K09B2S5D1JCA5TC4N
Run Details
Model:
Claude Opus 4.7
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
6.3s
Cost:
$0.009325
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
72.91%
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 Detective Marlowe stepped from his car into the gathering October storm. The wrought iron gates had been left open, which the butler mentioned was strictly against the late master's orders. Inside, seven guests waited in the drawing room, each clutching a glass of brandy with hands that trembled noticeably. Lord Ashcroft lay sprawled across the Persian rug, a silver letter opener buried deep between his shoulder blades. The grandfather clock in the corner had stopped at precisely eleven seventeen, which everyone agreed was the moment of death. Marlowe removed his dripping coat and studied each face in turn, noting the subtle flickers of fear and calculation. Someone in this room had committed murder, and that someone was currently pretending to mourn alongside the other innocent guests. The French windows stood locked from the inside, the only key dangling from the victim's own waistcoat pocket chain. Marlowe smiled grimly to himself because impossible crimes were precisely the sort of puzzle he had traveled here to solve.
created_at
"2026-04-24T13:32:07.33Z"
4/24/2026, 1:32:07 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1430
moderation_latency
(null)
generation_time
6070
tokens_prompt
46
tokens_completion
273
native_tokens_prompt
65
native_tokens_completion
360
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
0.009325
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"3733cb64-6423-4cba-a7a6-cfbf38e10391"
is_byok
false
latency
1430
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-1777037527-7aOP3JIgzpEWqitTGRBb"
session_id
(null)
api_type
"completions"
id
"gen-1777037527-Dhw8TqZMthRMnWSE0S0A"
upstream_id
"3733cb64-6423-4cba-a7a6-cfbf38e10391"
total_cost
0.009325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
72.91%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
19
2
19
3
18
4
20
5
19
6
20
7
19
8
20