NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPNAKD54B26H8A6H05GE4K
Run Details
Model:
Claude Opus 5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.6s
Cost:
$0.009850
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
84.26%
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 had been falling on Ashcombe Manor for three days, softening the lawns into something that swallowed footprints whole. Inspector Vale arrived at half past six, when the light was failing and the gravel drive shone like wet coal. Nobody came out to meet him, though he counted seven windows lit, and behind one of them a curtain twitched. The front door stood open six inches, which struck him as an invitation nobody living had bothered to extend. Inside, the hall smelled of beeswax, woodsmoke, and something faintly sweeter that he chose, for the moment, not to name. A grandfather clock near the staircase had stopped at twenty minutes past four, its pendulum hanging perfectly, unnaturally still. On the fourth step lay a single pearl earring, and on the sixth a smear the color of rust. Vale climbed slowly, counting stairs the way other men count prayers, and stopped where the landing turned toward the library. The door was locked from within, and beneath it a thin dark line was still creeping across the polished boards. He knocked twice, said his name and rank clearly, then heard a woman laughing somewhere far above his head.
created_at
"2026-07-25T13:15:32.342Z"
7/25/2026, 1:15:32 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1919
moderation_latency
(null)
generation_time
9536
tokens_prompt
46
tokens_completion
294
native_tokens_prompt
60
native_tokens_completion
382
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"
service_tier
"default"
usage
0.00985
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqYSDGqStA1DSa3oWYX"
is_byok
false
latency
1919
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784985332-z7wOMkeckcztD4C5pvum"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985332-258jUMISkK84C9Ft3YWp"
upstream_id
"msg_011CdNqYSDGqStA1DSa3oWYX"
total_cost
0.00985
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
84.26%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
19
4
20
5
19
6
19
7
20
8
20
9
19