NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYA8M1WXV4PYWD2VSC5AMNY
Run Details
Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.9s
Cost:
$0.000013
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
87.04%
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
Rain lashed against the windows, a gloomy, somber start. Detective Harding arrived, pulling his coat tight, feeling the dark. The mansion stood silent, shrouded in an eerie, chilling mist. A single scream echoed, disturbing the peaceful, quiet night. Lord Ashworth’s body lay sprawled, a horrifying, gruesome sight. Forensics began their work, meticulously examining the deceased man. A priceless antique dagger rested beside his lifeless hand now. The housekeeper wrung her hands, revealing a terrified, trembling face. Something felt terribly wrong, a disturbing, unsettling, hidden clue. This wealthy estate harbored secrets, undoubtedly a deadly, tragic scene.
created_at
"2026-02-20T20:01:09.191Z"
2/20/2026, 8:01:09 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
191
moderation_latency
(null)
generation_time
1766
tokens_prompt
63
tokens_completion
168
native_tokens_prompt
46
native_tokens_completion
137
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
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
0.0000128
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-Rw6HU6EVtQhs76a9pInZfVWY"
is_byok
false
latency
109
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771617669-k1qUb88ic1TwqscJSCUU"
upstream_id
"chatcmpl-Rw6HU6EVtQhs76a9pInZfVWY"
total_cost
0.0000128
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
87.04%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
10
2
10
3
9
4
9
5
9
6
10
7
10
8
9
9
10