NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCQY2Q28BSRR2PQNMTYRXXR
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
49.5s
Cost:
$0.115200
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
96.97%
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 Coldwater Lane since midnight, and by dawn it had washed the street clean again. Detective Inspector Ruth Mallory arrived at seven o'clock, holding a cold paper cup of coffee she had not yet tasted. The body lay in the doorway of number eleven, arms folded across the chest as if someone had carefully arranged them. Ruth crouched beside him and studied the face, which belonged to a man she had interviewed only last Tuesday afternoon. His name was Gerald Pike, and three days ago he had promised to tell her everything about the warehouse fire. Now his mouth was open slightly, as though his final sentence had been interrupted cleanly somewhere between thought and speech. There was no blood on the stone step, no wound she could see, no weapon lying anywhere nearby at all. Sergeant Okonjo waited beneath the shop awning, notebook open, pretending that the smell did not bother him in the least. "Who found him?" she asked, and the sergeant nodded toward a small woman shivering inside the bakery across the road. The baker's daughter opened the shop at five thirty and assumed he was a drunk sleeping off another rough night. Ruth stood, feeling the rain find the gap between her collar and her neck, and looked slowly up the street. Every window was dark and every curtain hung perfectly still, which interested her far more than the body itself did. Somebody on this quiet street had watched Gerald Pike die, and then folded his arms with slow, deliberate, unhurried care.
created_at
"2026-07-25T13:37:47.753Z"
7/25/2026, 1:37:47 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5280
moderation_latency
(null)
generation_time
49377
tokens_prompt
46
tokens_completion
1094
native_tokens_prompt
60
native_tokens_completion
4596
native_tokens_completion_images
(null)
native_tokens_reasoning
717
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
0.1152
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNsEt8yYX4QThRbse4H4"
is_byok
false
latency
1562
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-1784986667-ju86FTPxOZd0qvtFLBv9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784986667-vZTVsgoajGa2X0PHeaLt"
upstream_id
"msg_011CdNsEt8yYX4QThRbse4H4"
total_cost
0.1152
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
96.97%
Matches word count
n/a
neededClean
false
sentences
13
wordCounts
0
20
1
20
2
21
3
20
4
20
5
20
6
20
7
20
8
20
9
20
10
20
11
20
12
20