NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-01-01J94R68EBEV63TF0R4VRRHC1C
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
"Bill, this is insane! A kids' party? Seriously?" Molly chewed her lip as she sorted through a stack of mismatched invitations. "What's wrong with it? It's perfect. Kid parties - they serve up the pastry, ogle the activities, and get sugar bugged. Perfect for an unnoticed slip-in." Bill poured another cup of coffee and leaned against the bar. "Makes no sense. Security's going to be lax, I'll buy that. But, Molly, presents? There’s gotta be a better target." She slammed down a starry balloon. "Oh, so naive. Kid parties are hotspots. Families buy gold-plated first toys, custom name tags - we're talking swag you can't find elsewhere." Bill scoffed, "And you expect an army of little monsters to open up without throwing a fit?" Molly waved him off. "They won't know until it's too late. Worst-case scenario, I show up with a bucket of bubbles. Kids are allergic to 'no.'" "Except they will notice the presents missing," Bill countered. Molly grinned. "That's why we'll use magic in their eyes - a sprinkle of cookie dust. They'll think someone else took them. In and out, naptime spot, guaranteed." Bill sighed. "You can be such a meanie sometimes. Are you actually wearing sweaters and mittens for this?" She smirked. "Anything to play along till naptime hits. Bill, it's an upgrade, baby - a goldmine of childhood gifts and mini despairs. Count me in!"
id
"gen-1727810183-f7o6PIInTlubQi4wi8As"
total_cost
0.000183
upstream_id
"chatcmpl-c6ecc23d-0335-41ad-ad54-c22fd78ca5f0"
created_at
"2024-10-01T19:16:41.107692+00:00"
Tuesday, October 1st, 2024 at 7:16:41 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
66
moderation_latency
(null)
generation_time
17073
finish_reason
"stop"
tokens_prompt
67
tokens_completion
329
native_tokens_prompt
72
native_tokens_completion
330
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000183
Evaluation details
Result
Evaluator
Details
Meta Data
0.0304%
Matches word count
n/a
neededClean
false
words
230
49.9090%
Dialogue to Total Word Ratio
Ratio: 80.87%, Deviation: 9.13%
neededClean
false
wordsTotal
230
wordsDialogue
186
24.9697%