NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.5
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2026-02-08-01KGYYKV6W44CHG92RVYPGW5TG
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 old Victorian mansion stood silent against the stormy night sky, its windows dark except for one flickering light. Detective Sarah Chen stepped out of her car, rain pelting her face as she approached the imposing iron gates ahead. A uniformed officer waited nervously on the porch, his flashlight beam cutting through the heavy sheets of falling water outside. She had received the call at midnight, interrupting her first peaceful sleep in nearly three weeks of exhausting investigative work. The victim was wealthy industrialist Marcus Webb, found dead in his private study by his terrified young housekeeper this evening. No signs of forced entry existed anywhere in the house, which meant the killer likely knew the victim quite well indeed. Sarah pulled on latex gloves as she crossed the threshold, noting the expensive art pieces lining every wall of hallway. The body lay crumpled beside an ornate mahogany desk, a crystal whiskey glass shattered into tiny pieces on the floor. Blood pooled beneath his head from a wound that suggested someone had struck him with tremendous force from behind tonight. His eyes remained open, frozen in an expression of complete surprise, as though death had come from a trusted friend nearby.
created_at
"2026-02-08T15:41:14.592401+00:00"
Sunday, February 8th, 2026 at 3:41:14 PM GMT+00:00
model
"anthropic/claude-4.5-opus-20251124"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2545
moderation_latency
167
generation_time
7304
tokens_prompt
35
tokens_completion
232
native_tokens_prompt
44
native_tokens_completion
250
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00647
router
(null)
provider_responses
0
id
"8cb4d656-ee23-4baf-8a2c-1af0cdc3bb92"
status
200
is_byok
false
latency
2545
endpoint_id
"de32581c-2e11-4f54-8d29-e8a6e19d3038"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.5-opus-20251124"
api_type
"completions"
id
"gen-1770565266-1HCuzEY6kH7wMKlh7kGs"
upstream_id
"8cb4d656-ee23-4baf-8a2c-1af0cdc3bb92"
total_cost
0.00647
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
88.1959%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
19
1
20
2
20
3
20
4
20
5
21
6
20
7
20
8
20
9
21