NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-01-01J94R99GYGSHYFCRB3Q54X0MJ
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
"Don’t you watch the movies, Bill? Big-massive-event, everyone present, everybody’s distracted, ripe for the pickin’!" "You sure it'll work, Molly?" "It always works for Johnny Depp!" "Johnny Depp ain't bring nothing, Molly! It's just a buncha spoiled rich kids!" "Don’t talk bad about the rich, Bill. But we’re not stealing for the kids anyways. Are we?" "Nope, not our flies!" "I'm just saying, Bill, there could be assets worth more than the kids, and no one's watching." "Don't know if its the toys or the kids that are worth stealing from, Molly!" "Look, Bill, let me fill you in. You walk in every half hour in your robes and toothy grin. And you work your way to the entertainment lines. I'll probably be a costume expert. And I make a joke." "That's your plan?" "Sure is, Bill." "You ok with this, Molly? They’re just kids." "Oh knock it off Bill! Nothin' big, nothin' bad." "Ok, but remember, its forbidden to be mean to the kiddies!" "Even richer kiddies?" "You can spy and steal, but its bad luck." /assets/bd0b87b3-4fa4-4e24-8b47-bae2ac214a2b/2SchulzAmsterdam_158263-006.png
id
"gen-1727810283-3eDtwsvufJXFXWQnWXzU"
total_cost
0.0001735
upstream_id
"chatcmpl-ad59de38-fb31-4170-8afc-5f5658beefd8"
created_at
"2024-10-01T19:18:19.377606+00:00"
Tuesday, October 1st, 2024 at 7:18:19 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
107
moderation_latency
(null)
generation_time
15837
finish_reason
"stop"
tokens_prompt
67
tokens_completion
299
native_tokens_prompt
72
native_tokens_completion
311
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001735
Evaluation details
Result
Evaluator
Details
Meta Data
20.1897%
Matches word count
n/a
neededClean
false
words
180
45.1301%
Dialogue to Total Word Ratio
Ratio: 99.44%, Deviation: 9.44%
neededClean
false
wordsTotal
180
wordsDialogue
179
32.6599%