NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 10% dialogue
Run ID
2024-10-01-01J94R4BZN0HD64R4AXVKM15QP
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 paced the room, tossing a kid's toy figurine from one hand to the other. "Bill, we've got to be ready for this, man. It's chaos on steroids." Bill sat at the table, tapping out a rhythm with a banana peel. "Chaos? More like pandemonium, sweet cheeks. Think of all the candy, the cake, the party hats—complete sensory overload. And don't forget the kiddos." Molly sighed. "Yeah, yeah, the kiddos. That's the catch. You know their little faces when they catch us, don't you? It could derail the whole heist." Bill grinned, sliding a small device across the table. "Relax, partner. I've got a foolproof plan to distract the rugrats for as long as we need. All eyes on my pocket-sized projector." Molly picked up the device, examining it skeptically. "A video of a talking clown? Really?" Bill winked. "The educational value is off the charts, kiddo. Those little monkey brains will be mesmerized. And while they're enthralled, we'll make our move." Molly rolled her eyes but couldn't help smirking. "You've given me a headache just thinking about it, but fine. Clowns it is. Let's do this, Bill. These presents are as good as stolen." Bill raised his empty hand in triumph. "Go us! I love a plan that involves relentless joy and sticky fingers."
id
"gen-1727810121-n0wSfGuJmO8IrX9ewkZa"
total_cost
0.000173
upstream_id
"chatcmpl-3e1b32bd-f8f5-45cf-aae1-4b92c4a3a2e8"
created_at
"2024-10-01T19:15:49.751465+00:00"
Tuesday, October 1st, 2024 at 7:15:49 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
111
moderation_latency
(null)
generation_time
27595
finish_reason
"stop"
tokens_prompt
67
tokens_completion
310
native_tokens_prompt
72
native_tokens_completion
310
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000173
Evaluation details
Result
Evaluator
Details
Meta Data
43.3783%
Matches word count
n/a
neededClean
false
words
217
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.51%, Deviation: 60.51%
neededClean
false
wordsTotal
217
wordsDialogue
153
21.6892%