NC Bench
Overview
About
Tests
Models
Model
Magnum v2 72B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-01-01J94RB11T8KHP3C7R527RY5S3
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
Molly: "Alright Bill, here's the plan. We're going to sneak into little Timmy's birthday party and make off with all the presents." Bill: "You sure this is a good idea? I mean, it's just a bunch of kid's toys. Maybe we should go after something more valuable." Molly: "Shut up, do you want to do this or not?!" Bill: "Fine, fine, I'm in. But how do we get into a kid's birthday party without looking suspicious?" Molly: "Easy. Duh, we dress up like clowns. I've got the costumes and wigs right here in the trunk." Bill: "You're right, people will think we're performers hired for the party. Genius! Now what about the presents?" Molly: "I'll distract the parents with balloon animals, while you grab all the wrapped gifts. We toss them over the fence into the back of your pick-up truck." Bill: "Ah, it's gonna be like taking candy from a baby! ...Except they'll be crying about stolen toys instead."
id
"gen-1727810340-RvgHDjQxf8xcnpD1PAsL"
total_cost
0.0013005
upstream_id
"chatcmpl-e9ebde13-d782-43a8-8703-ad26ddeac3f8"
created_at
"2024-10-01T19:19:21.97267+00:00"
Tuesday, October 1st, 2024 at 7:19:21 PM GMT+00:00
model
"anthracite-org/magnum-v2-72b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
1044
moderation_latency
(null)
generation_time
20671
finish_reason
"stop"
tokens_prompt
67
tokens_completion
229
native_tokens_prompt
72
native_tokens_completion
229
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0013005
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
161
93.7942%
Dialogue to Total Word Ratio
Ratio: 95.03%, Deviation: 5.03%
neededClean
false
wordsTotal
161
wordsDialogue
153
46.8971%