NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8XHCH00B2A5AD5QDS0Y4A
Run Details
Model:
Claude Sonnet 5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.6s
Cost:
$0.005160
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
0.07%
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 Never Lies Detective Sarah Marlowe stood beneath the awning, watching rain pool around the victim's expensive shoes. Marcus Whitfield lay face-down, his silk tie soaked through with blood and rainwater mixing. The alley behind Whitfield Tower smelled of copper and wet garbage, an odd combination she'd never forget. Officer Chen approached carefully, holding his notebook against the downpour, trying to keep evidence dry. "No witnesses," he said, shaking water from his collar, looking thoroughly miserable already. Sarah crouched down, examining the wound angle, noting how precisely someone had planned this. The killer wanted him found exactly here, exactly like this. She glanced upward toward the fortieth floor, where lights still burned in Whitfield's office. Someone up there knew something, and she intended to discover who. The rain intensified suddenly, washing away footprints that might have offered crucial answers. Sarah pulled her coat tighter, feeling the case grow colder with each passing minute. "Get forensics here now," she ordered, standing slowly, her knees protesting the movement. Chen nodded, already dialing, while Sarah studied the building's shadowed entrance one last time. Something about this murder felt personal, deliberate, almost theatrical in its staging and execution. Whoever did this wanted attention, wanted the world to notice Marcus Whitfield's spectacular downfall. Sarah just needed to figure out why, and more importantly, who benefited most.
created_at
"2026-07-01T07:22:26.591Z"
7/1/2026, 7:22:26 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1582
moderation_latency
(null)
generation_time
9583
tokens_prompt
46
tokens_completion
378
native_tokens_prompt
60
native_tokens_completion
504
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
0.00516
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01QpXxKSUKTxmZuhRpdSbRSG"
is_byok
false
latency
1582
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-1782890546-vk6A4eTvzcvMW5e02J7k"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890546-257fHQGyOxgeT1rQJPAo"
upstream_id
"msg_01QpXxKSUKTxmZuhRpdSbRSG"
total_cost
0.00516
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
0.07%
Matches word count
n/a
neededClean
false
sentences
17
wordCounts
0
5
1
15
2
14
3
17
4
15
5
13
6
14
7
10
8
14
9
11
10
13
11
14
12
13
13
14
14
14
15
14
16
13