NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCR1N1E2KA1YAR7551GG969
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
44.4s
Cost:
$0.107475
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
77.78%
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 since midnight, and by dawn the gravel drive resembled a shallow river. Detective Inspector Marlowe Vance parked beside the fountain, stepped out, and immediately soaked both shoes in a widening brown puddle. A young constable waited under the portico, holding an umbrella that the wind had already bent into a useless shape. "He's in the library, ma'am," the constable said, "and nobody has touched anything, though the housekeeper very nearly fainted twice." Vance nodded, wiped rain from her eyes, and followed him into a hall that smelled of cold woodsmoke and lilies. Sir Edmund Ravensworth lay face down on the Persian carpet, one hand still gripping the crystal stopper of a decanter. Blood had dried black in his silver hair, and the fireplace poker lay barely three feet away, wiped suspiciously clean. Nine chairs surrounded the reading table, and eight of them had been pushed back hastily, as though abandoned in mid-sentence. Vance crouched, studied the dead man's face, and quietly asked how many guests had slept in the house last night. "Eight," the constable said, "and all eight of them insist they were asleep upstairs when the hall clock struck two." Outside, thunder rolled across the moor, and somewhere upstairs a door closed with a slow, practiced softness that suggested guilt.
created_at
"2026-07-25T13:39:44.822Z"
7/25/2026, 1:39:44 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4126
moderation_latency
(null)
generation_time
44338
tokens_prompt
46
tokens_completion
856
native_tokens_prompt
60
native_tokens_completion
4287
native_tokens_completion_images
(null)
native_tokens_reasoning
519
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
0.107475
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsPWEMLb94wJugJfuti"
is_byok
false
latency
1540
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-1784986784-muFzCtbPlFUUc6UFqrma"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986784-xeQwyVglHVmBAxHb2Wvc"
upstream_id
"msg_011CdNsPWEMLb94wJugJfuti"
total_cost
0.107475
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
77.78%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
20
3
40
4
20
5
20
6
20
7
20
8
40