NC Bench
Overview
About
Tests
Models
Model
Claude Opus 4.6
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2026-02-08-01KGYZQWTCDGDSSN44Z51M2NRW
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 mansion stood silently at the end of Maple Drive, its windows dark against the cold November sky above. Detective Sarah Chen stepped out of her unmarked sedan and pulled her coat tighter against the bitter wind blowing hard. Yellow crime scene tape fluttered between two oak trees, marking the boundary where normal life ended and death's work began. A uniformed officer approached her with a clipboard in hand, his face pale and drawn from what he had seen. "The body is in the study on the second floor," he said quietly, his voice barely rising above the wind. Sarah nodded and walked up the cracked stone path, her boots crunching on fallen leaves scattered across the neglected ground. The front door hung open like a mouth frozen in a scream, revealing the dark hallway that stretched beyond its frame. She could smell it before she saw anything—the unmistakable metallic scent of blood mixed with expensive perfume lingering in air. On the mahogany desk lay a woman in a red silk dress, her lifeless eyes staring up at the ceiling. A single playing card, the queen of spades, had been placed deliberately in her right hand by whoever killed her. Sarah studied the scene carefully, knowing that somewhere in this room the killer had left behind the clue to everything.
created_at
"2026-02-08T16:01:07.264739+00:00"
Sunday, February 8th, 2026 at 4:01:07 PM GMT+00:00
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2430
moderation_latency
254
generation_time
8572
tokens_prompt
35
tokens_completion
254
native_tokens_prompt
44
native_tokens_completion
288
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
0.00742
router
(null)
provider_responses
0
status
(null)
is_byok
false
latency
10046
endpoint_id
"c926c048-563e-44b0-8434-95965bee924c"
provider_name
"Anthropic"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
1
id
"2f9039f6-709c-4267-919d-3910fbd20b39"
status
200
is_byok
false
latency
2430
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-opus-20260205"
api_type
"completions"
id
"gen-1770566447-3Z3OSdkDvuXP4SJjgF2z"
upstream_id
"2f9039f6-709c-4267-919d-3910fbd20b39"
total_cost
0.00742
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
92.8460%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
21
7
21
8
20
9
20
10
20