NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYA8P69CMGEM985XRH5R6J6
Run Details
Model:
Grok 4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
21.5s
Cost:
$0.008792
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
38.68%
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 ancient manor loomed under a thunderous sky, its jagged silhouette piercing the night as rain lashed the overgrown gardens relentlessly. Inside, flickering candlelight danced on ornate walls, casting long shadows that whispered secrets from a bygone era of wealth and intrigue. Lady Elara glided through the grand hallway, her silk gown rustling softly, eyes scanning the assembled guests with calculated suspicion and hidden dread. Lord Harrington raised his glass in a toast, his voice booming over the storm, masking the tension that simmered beneath polite smiles. Suddenly, a piercing scream echoed from the library, freezing everyone in place as the sound shattered the fragile veneer of civility. Detective Thorne burst into the room, his coat dripping rainwater, badge gleaming under the chandelier as he surveyed the chaotic scene intently. A lifeless body lay sprawled on the Persian rug, blood pooling around the antique dagger embedded deep in the victim's chest.
created_at
"2026-02-20T20:01:11.386Z"
2/20/2026, 8:01:11 PM
model
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
14852
moderation_latency
(null)
generation_time
21386
tokens_prompt
46
tokens_completion
256
native_tokens_prompt
719
native_tokens_completion
550
native_tokens_completion_images
0
native_tokens_reasoning
367
native_tokens_cached
718
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
"completed"
usage
0.0087915
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"79706a68-0ded-8ece-e006-296f591cd89f"
is_byok
false
latency
446
model_permaslug
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771617671-UY3NVsreUOPkLOdfqzn4"
upstream_id
"79706a68-0ded-8ece-e006-296f591cd89f"
total_cost
0.0087915
cache_discount
0.0016155
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
38.68%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
21
1
21
2
23
3
22
4
21
5
22
6
21