NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8B8VNEK0SSX4PV0QKGJWZ
Run Details
Model:
Gemma 3 12B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.5s
Cost:
$0.000019
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
89.63%
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 manor windows, a mournful, steady beat. Inside, Lord Ashworth lay lifeless upon the Persian rug. A single crimson stain blossomed on his tailored tweed jacket. Detectives Harding and Davies arrived promptly, facing a grim scene. The grand library stood silent, filled with shadows and old books. Lady Ashworth wept dramatically, clutching a delicate porcelain teacup. A faint scent of almonds lingered, subtly permeating cool air. The butler, Jeeves, maintained composure, offering weak, apologetic murmurs. A priceless antique clock ticked loudly, marking passing, crucial moments. Everyone present appeared nervous, concealing secrets deep within their hearts.
created_at
"2026-02-20T19:27:38.881Z"
2/20/2026, 7:27:38 PM
model
"google/gemma-3-12b-it"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
132
moderation_latency
(null)
generation_time
3431
tokens_prompt
63
tokens_completion
172
native_tokens_prompt
46
native_tokens_completion
132
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
0.000019
router
(null)
provider_responses
0
endpoint_id
"eb06dc92-5a16-47ec-a776-6ef956457c47"
id
"chatcmpl-RUvWnpvCaNoLRp71CcKobkFT"
is_byok
false
latency
50
model_permaslug
"google/gemma-3-12b-it"
provider_name
"DeepInfra"
status
200
api_type
"completions"
id
"gen-1771615658-Knt6m4eZiClCzRgOHkOd"
upstream_id
"chatcmpl-RUvWnpvCaNoLRp71CcKobkFT"
total_cost
0.000019
cache_discount
(null)
upstream_inference_cost
0
provider_name
"DeepInfra"
Evaluation details
Result
Evaluator
Details
Meta Data
89.63%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
9
2
10
3
10
4
11
5
9
6
10
7
9
8
10
9
10