NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9V4CVA6DJT502TP6V5EC2
Run Details
Model:
Grok 4
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
15.9s
Cost:
$0.008686
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
68.52%
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 fog-shrouded streets of Victorian London whispered secrets as Inspector Eliza Thorn approached the dimly lit alleyway crime scene. A lifeless body lay sprawled on cold cobblestones, its eyes wide open in eternal shock from an unseen assailant. She knelt down carefully to examine the victim, noting a peculiar silver locket clutched tightly in the rigid fingers. Footsteps echoed suddenly from the shadows nearby, prompting Eliza to draw her revolver while scanning the misty surroundings alertly. A mysterious figure emerged slowly into the lamplight, hands raised in surrender, claiming to have witnessed the brutal murder moments earlier.
created_at
"2026-02-20T19:53:47.173Z"
2/20/2026, 7:53:47 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
11269
moderation_latency
(null)
generation_time
15835
tokens_prompt
46
tokens_completion
169
native_tokens_prompt
719
native_tokens_completion
543
native_tokens_completion_images
0
native_tokens_reasoning
423
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
0.0086865
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"5f150f17-1f6d-51f4-52ce-de4c76a1b202"
is_byok
false
latency
73
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-1771617227-8UYITg1cByKyIUQftRi9"
upstream_id
"5f150f17-1f6d-51f4-52ce-de4c76a1b202"
total_cost
0.0086865
cache_discount
0.0016155
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.52%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
19
2
19
3
19
4
21