NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEAGYMK1AN2XRZ5062B639B
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
42.0s
Cost:
$0.059740
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
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 fell steadily on the old manor's rooftop, while shadows crept slowly across the darkened, silent hallways within its walls. Detective Sarah Mills stood quietly beneath the grand old entrance, staring intently at the heavy oak door left slightly ajar. Something felt terribly wrong that evening, as an eerie silence hung heavily over the once peaceful, elegant countryside estate grounds. She pushed the heavy door open carefully, revealing a dimly lit foyer filled with broken glass and overturned antique furniture. A single scream had echoed loudly through the darkened halls only minutes before, sharp and full of pure terror still. Now, only silence remained, broken faintly by Sarah's own careful, measured footsteps echoing slowly across the cold marble floor below. Then she saw it clearly now: a man's body lying motionless near the base of the grand old marble staircase. Blood pooled slowly beneath him, dark and glistening under the dim light of the flickering old brass chandelier above her.
created_at
"2026-07-01T07:50:31.327Z"
7/1/2026, 7:50:31 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3672
moderation_latency
(null)
generation_time
41927
tokens_prompt
46
tokens_completion
723
native_tokens_prompt
60
native_tokens_completion
5962
native_tokens_completion_images
(null)
native_tokens_reasoning
471
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
0.05974
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_016DPy9rkod34gjo4KD4Whmj"
is_byok
false
latency
1645
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782892231-Cvj1BEmmcPwNwiQUnbaC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892231-iTWPjU1tAbSSGxwAhmqQ"
upstream_id
"msg_016DPy9rkod34gjo4KD4Whmj"
total_cost
0.05974
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
100.00%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20