NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9BCRTD7QMM0QJEF1CYTXC
Run Details
Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.4s
Cost:
$0.000012
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
51.58%
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 dismal, grey scene. Detective Harding arrived, surveying the opulent, silent room. A single gunshot echoed, a chilling, terrible decree. The victim lay motionless, a wealthy, prominent businessman now. His expensive suit covered in crimson, a gruesome, awful sight. Harding questioned the butler, a nervous, trembling, anxious man. “I heard nothing unusual,” the butler desperately started speaking. “Just the rain and the clock, relentlessly ticking on.” A priceless painting hung above, reflecting the morbid glow. “Someone clearly wanted him silenced, brutally, violently, sadly.”
created_at
"2026-02-20T19:45:11.463Z"
2/20/2026, 7:45:11 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
44
moderation_latency
(null)
generation_time
1166
tokens_prompt
63
tokens_completion
161
native_tokens_prompt
46
native_tokens_completion
129
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
0.00001216
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-Rv8vsiSBAwKXa41xMT3O2nUS"
is_byok
false
latency
18
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771616711-OaYq6jjcQkl2L8jZxkRK"
upstream_id
"chatcmpl-Rv8vsiSBAwKXa41xMT3O2nUS"
total_cost
0.00001216
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
51.58%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
9
1
8
2
8
3
9
4
10
5
9
6
27
7
8