NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYB8MGC1ZQ1SVGRVA38HTKB
Run Details
Model:
Gemma 3 4B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.6s
Cost:
$0.000012
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
88.48%
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, gray scene. Detective Harding surveyed the opulent, unsettling study now grim. Crimson stained the Persian rug, a horrifying, brutal sight. The victim lay motionless, a wealthy, influential man, quite still. A single gunshot echoed, announcing a terrible, sudden death now. Harding noted the scattered papers, suggesting furious, hurried work. The air hung heavy with perfume, a cloying, sickly scent. A priceless antique clock ticked, marking time’s slow, steady pace. His partner joined him, observing this tragic, awful display fully.
created_at
"2026-02-20T20:18:38.232Z"
2/20/2026, 8:18:38 PM
model
"google/gemma-3-4b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
146
moderation_latency
(null)
generation_time
1470
tokens_prompt
63
tokens_completion
147
native_tokens_prompt
46
native_tokens_completion
122
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
0.0000116
router
(null)
provider_responses
0
endpoint_id
"d3de3bd4-81bc-48fb-924f-2a87b2a36e75"
id
"chatcmpl-RuEGugDXpIXF3erEtkLtsPK0"
is_byok
false
latency
48
model_permaslug
"google/gemma-3-4b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771618718-nIZFrXTDXjPOpEy1yeFH"
upstream_id
"chatcmpl-RuEGugDXpIXF3erEtkLtsPK0"
total_cost
0.0000116
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
88.48%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
9
1
9
2
9
3
10
4
10
5
9
6
10
7
10
8
10