NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7MNPY980JCPA07166VGX2
Run Details
Model:
Grok 4
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
12.6s
Cost:
$0.006779
Provider:
xAI
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 fog-shrouded mansion loomed ominously under the full moon's glow. Eleanor discovered the body sprawled lifeless in the grand library. Blood pooled around the victim, staining the antique Persian rug. She gasped, her hand trembling as she clutched the doorframe. Footsteps echoed from the hallway, approaching with deliberate, slow steps. The butler appeared, his face pale and eyes wide with shock. "Who could have done this terrible deed?" Eleanor whispered hoarsely. Shadows danced on walls, hiding secrets in every dark corner. A distant clock struck midnight, marking the hour of mystery. Outside, thunder rumbled, as rain began to pelt the windows.
created_at
"2026-02-20T19:15:18.38Z"
2/20/2026, 7:15:18 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
7618
moderation_latency
(null)
generation_time
12315
tokens_prompt
46
tokens_completion
176
native_tokens_prompt
719
native_tokens_completion
410
native_tokens_completion_images
0
native_tokens_reasoning
266
native_tokens_cached
679
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
0.00677925
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"b5cbbd88-d13c-2c05-c79e-93e6bf9639e0"
is_byok
false
latency
507
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-1771614918-cJ9aUOk9NuDnMw5cnwzE"
upstream_id
"b5cbbd88-d13c-2c05-c79e-93e6bf9639e0"
total_cost
0.00677925
cache_discount
0.00152775
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
94.82%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
11
1
10
2
10
3
10
4
10
5
11
6
10
7
10
8
10
9
10