NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRJ63T7BRD747HB3QBF9TG
Run Details
Model:
Claude Opus 5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
18.3s
Cost:
$0.041350
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
72.60%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain had washed the gravel drive clean by dawn. Inspector Marlowe parked beside the fountain and killed the engine. Ravenscourt House loomed above him, all wet stone and silence. A constable waited at the door, hat clutched in hands. The young man's face had gone the color of ash. "Library, sir," he said. "Nobody has touched anything since seven." Marlowe wiped his shoes and stepped into the warm hall. Somewhere upstairs a woman was weeping without any real conviction. The library smelled of brandy, book dust, and cold iron. Lord Ravenscourt sat in his chair, facing the tall windows. Someone had driven a letter opener through his starched collar. His right hand still held a pen above blank paper. Marlowe crouched, studying the neat wound and the untouched glass. The man had not struggled, had not even stood up. "He knew them," Marlowe murmured, "and he trusted them completely." Behind him, the constable finally asked who should be woken. Marlowe rose slowly and looked at the ceiling above them. "Everyone," he said. "One of them will lie to me."
created_at
"2026-07-25T13:48:46.596Z"
7/25/2026, 1:48:46 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3928
moderation_latency
(null)
generation_time
18185
tokens_prompt
46
tokens_completion
446
native_tokens_prompt
60
native_tokens_completion
1642
native_tokens_completion_images
(null)
native_tokens_reasoning
177
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
0.04135
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNt5SN3VT4kKkczcGF57"
is_byok
false
latency
1275
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-1784987326-wELiBGh7PtQ5SmXihi85"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987326-P016MN6MKCesUmszUsD4"
upstream_id
"msg_011CdNt5SN3VT4kKkczcGF57"
total_cost
0.04135
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
72.60%
Matches word count
n/a
neededClean
false
sentences
18
wordCounts
0
10
1
10
2
10
3
10
4
10
5
4
6
16
7
10
8
10
9
10
10
10
11
10
12
10
13
10
14
20
15
10
16
3
17
7