NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-10-01-01J94QZEX1ESNJK8TZNW4CM4CB
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
On a rainy Saturday, Molly and Bill huddled under an umbrella, swirling up paper cups of cheap tea. "Well, here's the deal. We aim for cribs and walkers; ducklings and frisbees. Anything too small or too big they just chuck in the garbage, so we're looking for precious bits for black market import, and Mommy's little darling's tiny obsession." Bill chimed in. "Then what? A breakdown of the operation." "Operation, huh? It's not big enough to be an operation." "We need to be precise." "And careful. Sure, thirty presents is their target, eighty-profit, a solid seventy-eight for us after deductions," she whistled, tapping her foot to the rhythm. "We go through the kids' list, pinpoint down with a sharp pencil where we think the heavy stuff, like laptops, are likely to fall." "Hey!" Bill leaned in. "Why not just snatch the full goody bags while the kids are playing?" The rain drummed faster, busier, like there were fifty pencils once more in the process of negotiation.
id
"gen-1727809960-o1jmVjFUaVYkbbwvPbxg"
total_cost
0.0001305
upstream_id
"chatcmpl-e17fd67d-5c4a-47ea-a400-f4ba88819c80"
created_at
"2024-10-01T19:12:53.076624+00:00"
Tuesday, October 1st, 2024 at 7:12:53 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
113
moderation_latency
(null)
generation_time
11701
finish_reason
"stop"
tokens_prompt
67
tokens_completion
225
native_tokens_prompt
72
native_tokens_completion
225
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001305
Evaluation details
Result
Evaluator
Details
Meta Data
0.0028%
Matches word count
n/a
neededClean
false
words
168
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.83%, Deviation: 20.83%
neededClean
false
wordsTotal
168
wordsDialogue
119
0.0014%