NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-23-01J3G80F0WD0M5QRRX6H7FHN33
Run Details
Model:
Llama 3.1 8B
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.1s
Cost:
$0.000036
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
95.29%
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
Detective Jameson stepped out of his office into the morning sunlight. Cold rain dripped steadily from the eaves of the building. Frustrated with the case sitting on his desk all day. He thought about the victim's last words to his wife. The police database revealed nothing about the caller's voice tone. Police officials hesitated to release any details to the press. Local news stations camped outside the precinct building all night. The city's mayor demanded action and a quick case solve. Jameson hoped that a meeting with the chief would. Bring some much-needed clarity and a direction for the case. Their conversation was scheduled for one o'clock that afternoon meeting.
id
"gen-ZrAUlJ4Vu4TXw2zy1lHB6ISzowaN"
total_cost
0.0000364
upstream_id
"6cfff3d0-1fec-4c4c-9d3b-3066be5c4afb"
created_at
"2024-07-23T16:50:20.232537+00:00"
7/23/2024, 4:50:20 PM
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
638
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
76
tokens_completion
136
native_tokens_prompt
44
native_tokens_completion
138
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000364
Evaluation details
Result
Evaluator
Details
Meta Data
95.29%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
11
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
9
9
10
10
10