NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8QZ9YXNNV5XQGRHHXBMWP
Run Details
Model:
Grok 4
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
9.7s
Cost:
$0.004831
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
77.46%
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
Fog shrouded the old mansion on the hill that night. Detective Jane Harrow arrived just as rain began to fall. She stepped inside, her boots echoing on marble floors. The host lay lifeless in the grand dining room. Guests gathered around, their faces pale with shock and fear. A bloody knife rested beside the victim's cold hand. Jane scanned the room for any signs of struggle. Suspects whispered among themselves, eyes darting suspiciously around. Thunder crashed outside, heightening the tension in the air. Who among them held the secret to this crime?
created_at
"2026-02-20T19:34:35.084Z"
2/20/2026, 7:34:35 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
6005
moderation_latency
(null)
generation_time
9618
tokens_prompt
46
tokens_completion
151
native_tokens_prompt
719
native_tokens_completion
286
native_tokens_completion_images
0
native_tokens_reasoning
167
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
0.0048315
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"140ea99e-5ad9-cd74-9bf4-3fa5779c5279"
is_byok
false
latency
828
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-1771616075-kcPYG2prDTJ5qzaCIp0F"
upstream_id
"140ea99e-5ad9-cd74-9bf4-3fa5779c5279"
total_cost
0.0048315
cache_discount
0.0016155
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
77.46%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
9
3
9
4
10
5
9
6
9
7
8
8
9
9
9