NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFKAC563W4CCD05XNZK3CZX
Run Details
Model:
Stealth: Healer Alpha
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
5.1s
Cost:
$0.000000
Provider:
Stealth
Evaluation summary
Score
Evaluator
Details Link
94.82%
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 body was found at precisely three in the morning. Rain hammered the windows like accusations from a gray sky. Detective Marsh stood at the doorway, breathing the cold air. The victim was the richest man in town, Mr. Crane. There was no weapon nearby, no wound upon his skin. His eyes remained open, staring at something unseen by us. Someone had poisoned his evening whiskey, it seemed quite certain. The clock ticked onward, indifferent to the silence inside. Three suspects waited downstairs, each with their own dark secrets. Detective Marsh whispered, "This case will break someone's world."
created_at
"2026-03-11T23:22:10.993Z"
3/11/2026, 11:22:10 PM
model
"openrouter/healer-alpha"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2947
moderation_latency
(null)
generation_time
5000
tokens_prompt
46
tokens_completion
740
native_tokens_prompt
2119
native_tokens_completion
667
native_tokens_completion_images
(null)
native_tokens_reasoning
590
native_tokens_cached
2117
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
router
(null)
provider_responses
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773271330-1bx4huLKMI0MKgbBKNge"
upstream_id
"gen-1773271330-1bx4huLKMI0MKgbBKNge"
total_cost
0
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Stealth"
Evaluation details
Result
Evaluator
Details
Meta Data
94.82%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
9
8
10
9
9