NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQQPSBG6F819SA9RKXDDAC
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
33.6s
Cost:
$0.080225
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.00%
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 rain had been falling on Ashgrove Manor since midnight, and by dawn the gravel drive resembled a shallow river. Inspector Halloran parked beside the fountain, turned off the engine, and sat listening to water drumming against the car roof. A young constable waited under the portico, hatless, pale, holding an umbrella that the wind had already turned inside out. "She's in the library, sir," he said, "and nobody has touched her, though the housekeeper wanted to cover her face." Halloran nodded, wiped rain from his eyes, and followed the boy through doors of oak into the cold echoing hall. Fourteen guests had come for the weekend shooting party, and every one of them now stood accused by the silence. Lady Marchmont lay across the Persian carpet with her arms flung wide, as though welcoming home an unexpected late guest. The letter opener between her ribs bore the Marchmont crest, and the fire had burned itself down to grey embers. Rain hammered the tall windows like impatient knuckles, and the great old house seemed to hold its breath and wait. Halloran crouched, studied the clean edges of the wound, and understood at once that this particular killer had not hesitated. Somewhere above him a floorboard creaked, and he thought, quite calmly: one of you is still awake and still listening.
created_at
"2026-07-25T13:34:18.931Z"
7/25/2026, 1:34:18 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4576
moderation_latency
(null)
generation_time
33429
tokens_prompt
46
tokens_completion
682
native_tokens_prompt
60
native_tokens_completion
3197
native_tokens_completion_images
(null)
native_tokens_reasoning
355
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
0.080225
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNryV3zRZW83JkhMmNcw"
is_byok
false
latency
1573
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-1784986458-P5tJ7iZzYht8gMOlesua"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986458-oAoBsuIyRSwRiBSVTEbD"
upstream_id
"msg_011CdNryV3zRZW83JkhMmNcw"
total_cost
0.080225
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
90.00%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
40
4
20
5
20
6
20
7
20
8
20
9
20