NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-10-01-01J94QWMTK6G4BSZT4WRNRP7PB
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 pulled out a stack of invitations. "I got us in as the aunt and uncle of the birthday boy." Bill frowned. "Aunt and uncle you say? That's... very sneaky." "Just go with it, smarty pants." Molly tossed him a wig and a pair of horn-rimmed glasses. "You're going to need this." "What, I thought I could go in my natural glory? Like the bank job?" Bill chuckled, replacing his hair with the gray wig, gasses sliding down his nose. "Please, has anyone ever taken you seriously as anyone other than an uncle?" Molly grabbed a box labeled 'Need Outlet.' "And here's what you'll be handing me as you walk out. Bonus points if you can pull off an effusive good-bye to the parents." Bill snatched the present box and pranced over to the mirror, preening. "Ta-da!" Molly groaned as he bopped around hat in hand. "The effeminate code is off. You're always butch. Keep that up and I might have to call the whole thing off."
id
"gen-1727809868-pXMO73gUrNU6jtDX8M8K"
total_cost
0.000132
upstream_id
"chatcmpl-67d9342a-e681-4da9-9212-099246314028"
created_at
"2024-10-01T19:11:21.338427+00:00"
Tuesday, October 1st, 2024 at 7:11:21 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
524
moderation_latency
(null)
generation_time
11604
finish_reason
"stop"
tokens_prompt
67
tokens_completion
228
native_tokens_prompt
72
native_tokens_completion
228
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000132
Evaluation details
Result
Evaluator
Details
Meta Data
0.0304%
Matches word count
n/a
neededClean
false
words
170
0.0000%
Dialogue to Total Word Ratio
Ratio: 50.59%, Deviation: 40.59%
neededClean
false
wordsTotal
170
wordsDialogue
86
0.0152%