NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8VMX5JA2KVJV4JZ34RKGR
Run Details
Model:
Claude Sonnet 5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.1s
Cost:
$0.004950
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
0.00%
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
# The Last Guest Rain hammered the old mansion's windows while thunder rolled across the darkened hills outside town. Detective Sarah Chen arrived precisely when the storm reached its most dramatic and violent peak. She noticed the front door standing open, swinging gently despite the absence of any breeze. Inside, seven guests huddled together, their faces pale beneath the flickering candlelight above them. The host, Marcus Webb, lay motionless on his study floor, blood pooling beneath him. Nobody had heard anything unusual, they claimed, despite the storm's relatively quiet moments throughout evening. Sarah studied each face carefully, searching for the smallest crack in their composure. The butler mentioned finding the body precisely at nine, right after the lights flickered. A shattered wine glass lay near the victim, its crimson contents mixing with actual blood. Someone had extinguished the fireplace deliberately, leaving the room colder than the rest of the house. Sarah crouched beside the body, examining the wound with her flashlight's narrow beam. "This wasn't a robbery," she muttered, noting the untouched safe behind the painting. Six suspects remained in that house, each harboring secrets darker than the storm outside. The power flickered again, plunging everyone into three seconds of absolute, terrifying darkness. When light returned, Sarah realized someone else had vanished from the room entirely. The game, she realized grimly, had only just begun tonight.
created_at
"2026-07-01T07:21:24.658Z"
7/1/2026, 7:21:24 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1670
moderation_latency
(null)
generation_time
9051
tokens_prompt
46
tokens_completion
375
native_tokens_prompt
60
native_tokens_completion
483
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
0.00495
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01AZMKeeKFhvzQp8yt8FVX3w"
is_byok
false
latency
1669
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-1782890484-dBlNjfBjlCpNvnGvAXGH"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890484-j4gdBXRilpx61G7NI7x6"
upstream_id
"msg_01AZMKeeKFhvzQp8yt8FVX3w"
total_cost
0.00495
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
0.00%
Matches word count
n/a
neededClean
false
sentences
17
wordCounts
0
4
1
15
2
15
3
15
4
14
5
14
6
15
7
13
8
14
9
15
10
16
11
13
12
13
13
14
14
13
15
13
16
10