NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-18-01KHQ94DFFT825B3S3E7W3B85B
Run Details
Model:
Claude Sonnet 4.6
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.6s
Cost:
$0.003417
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
34.48%
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 old lighthouse stood at the edge of town, its beam cutting through the thick autumn fog relentlessly. Detective Clara Marsh arrived at the scene just after midnight, her boots crunching softly on the wet gravel. A body had been found slumped against the rusty iron door, one hand clutching a torn photograph tightly. The victim was a man in his fifties, well dressed, with no obvious signs of struggle anywhere nearby. Clara pulled on her gloves and knelt beside him, studying his pale face with quiet, methodical professional focus. Her partner, Officer Reed, stood behind her scribbling notes into a small weathered notebook he always carried with him. The lighthouse keeper claimed he had heard nothing unusual, though his nervous eyes suggested a very different story entirely. Waves crashed loudly against the rocks below as Clara noticed a single gold ring missing from his right hand. Someone had been here before them, that much was certain, and they had taken something important deliberately away tonight.
created_at
"2026-02-18T02:26:47.775797+00:00"
2/18/2026, 2:26:47 AM
model
"anthropic/claude-4.6-sonnet-20260217"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
650
moderation_latency
162
generation_time
5326
tokens_prompt
46
tokens_completion
269
native_tokens_prompt
44
native_tokens_completion
219
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
0.003417
router
(null)
provider_responses
0
id
"101229e4-7149-48ea-a1e8-dcdb72775757"
status
200
is_byok
false
latency
650
endpoint_id
"83d802cb-44f2-45a0-a9d5-cb9bf79777c8"
provider_name
"Amazon Bedrock"
model_permaslug
"anthropic/claude-4.6-sonnet-20260217"
api_type
"completions"
id
"gen-1771381601-FLxk8hxqKRXGIOc1GclS"
upstream_id
"101229e4-7149-48ea-a1e8-dcdb72775757"
total_cost
0.003417
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
34.48%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
18
1
18
2
18
3
18
4
18
5
19
6
19
7
19
8
19