NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRCVWE2DET7ASSS7CR12H3
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
24.3s
Cost:
$0.056850
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
95.63%
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 Ashgrove Manor since midnight, and by dawn the gravel drive resembled a shallow river. Miss Edith Prine noticed the library door standing open, which had never once happened in eleven years of faithful service. She carried the breakfast tray inside, expecting to find the colonel asleep in his chair beside the cold grey fireplace. Instead she found him face down upon the Persian carpet, one hand outstretched toward the telephone he had never reached. The tray struck the floor and the teapot shattered, spraying hot brown Darjeeling across the dead man's polished riding boots. Nobody in the house heard her scream, because the storm had swallowed every sound the old stone walls could produce. By seven o'clock, when the cook finally came looking, the fire had died and rain streaked the tall east windows. Edith sat on the bottom stair, hands folded, whispering over and over that she had locked that door herself. Sergeant Bell arrived at nine, soaked through, and asked which of the eleven guests had most wanted Colonel Fairbourne dead.
created_at
"2026-07-25T13:45:52.278Z"
7/25/2026, 1:45:52 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4559
moderation_latency
(null)
generation_time
24184
tokens_prompt
46
tokens_completion
636
native_tokens_prompt
60
native_tokens_completion
2262
native_tokens_completion_images
(null)
native_tokens_reasoning
367
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
0.05685
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsrbKCPQeB9EwkfiByn"
is_byok
false
latency
1612
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-1784987152-Y1WXtzxDVgGbskyJGTLD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987152-ACzMkMb1ZQg6mrAHloFs"
upstream_id
"msg_011CdNsrbKCPQeB9EwkfiByn"
total_cost
0.05685
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
95.63%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
19
8
20