NC Bench
Overview
About
Tests
Models
Model
Gemma 2 27B
Test
N-Length Sentences
Scenario
Write sentences with 20 words each
Run ID
2024-07-14-01J2SC65J5N21Y9DR61YP5V0QR
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain lashed against the library windows, blurring the gaslight glow filtering through. Moonlight painted the scene in a ghostly light, illuminating the sprawling chaos within. Books were strewn across the floor, their pages scattered like fallen leaves. A single shaft of light shone on a figure crumpled amidst the overturned chairs and fallen tomes, a face frozen in an expression of perpetual surprise under a dusty pile of leather-bound volumes. Her emerald green dress lay in a twisted heap on the floor, books littering it. The library was silent, save for the steady drumming of heavy, unforgiving rain. Inspector Davies pushed open the door, his trench coat dripping onto the worn rug. "Another one, Mr. Blackwood?" he asked, his voice tinged with skepticism and weariness. Blackwood, pale as death itself, merely nodded, staring listlessly at the scattered papers. The victim was Charlotte, his wife, who wear a pajama set specifically tailored for the occasion. Her usually vibrant blue eyes, rimmed by thick lashes, were now lifeless and dull, lusterless under the wavering light. Davies sighed, knowing another night of unraveling secrets and lies stretched before him.
id
"gen-WZYds4VGW4AhFKulcmpqU8geaAw5"
total_cost
0.00007722
upstream_id
"cmpl-1b3fa098e6fc4cc697e2c86d66b6b051"
created_at
"2024-07-14T19:40:58.511143+00:00"
Sunday, July 14th, 2024 at 7:40:58 PM GMT+00:00
model
"google/gemma-2-27b-it"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepInfra"
latency
8752
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
54
tokens_completion
253
native_tokens_prompt
46
native_tokens_completion
240
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00007722
Evaluation details
Result
Evaluator
Details
Meta Data
5.0572%
Matches word count
n/a
neededClean
false
sentences
12
wordCounts
0
13
1
13
2
12
3
34
4
15
5
13
6
14
7
13
8
13
9
16
10
19
11
13