NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-10-01-01J94RH1774RH352X4BT67PFX1
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly and Bill sat at a small table in Molly's cluttered apartment, poring over a detailed diagram of the crime scene. Molly: "Alright Bill, we know the basics - the party, the gifts, and a room for three kids. But those little monsters could bring down any plan." Bill: "Worked for El Chapito and the Krabby Patty heist. What's different here?" Molly: "Well, for one El Chapito took years to train, and Krabby Patties aren't nearly as valuable as luxury toys. And no clowns to deal with." Bill: "I get the toys part, but why would clowns matter?" Molly: "Don't you know anything? Children love clowns, and who wears clown makeup? Santa Claus and entire gangs." Bill: "Point is, what's your plan genius?" Molly: "My plan is simple - you distract the clowns, I'll be in and out grabbing the loot." Bill: "But you didn't answer my question - how do you expect a clown to be distracted?" Molly: "I haven't quite figured that part out yet... I'll let you know when I have an idea." Bill sighed heavily as Molly scribbled some more notes onto their hastily drawn map.
id
"gen-1727810537-oQLocTj8U63HhDHCHFA4"
total_cost
0.0001515
upstream_id
"chatcmpl-07fd22eb-1489-4903-a16e-c0e293ee279e"
created_at
"2024-10-01T19:22:34.557397+00:00"
Tuesday, October 1st, 2024 at 7:22:34 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
250
moderation_latency
(null)
generation_time
16487
finish_reason
"stop"
tokens_prompt
67
tokens_completion
267
native_tokens_prompt
72
native_tokens_completion
267
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001515
Evaluation details
Result
Evaluator
Details
Meta Data
75.1556%
Matches word count
n/a
neededClean
false
words
187
0.0000%
Dialogue to Total Word Ratio
Ratio: 76.47%, Deviation: 66.47%
neededClean
false
wordsTotal
187
wordsDialogue
143
37.5778%