NC Bench
Overview
About
Tests
Models
Model
Qwen 2 72B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-07-19-01J35SN27WEPQJKP8F7G6EGPHE
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
Molly tapped her chin, eyeing the blueprint of the McAllisters' backyard like it was a treasure map. "Okay, here's the plan. I'll be the magician's assistant." "And I'll be the clown?" Bill asked, stuffing his face with a doughnut. "No, you'll be the balloon artist. Your job is to keep the kiddies busy with balloon animals while I slip away to pocket the loot." Bill looked at her incredulously. "Balloon animals? You think I can do balloon animals?" "Sure, it's easy! You just twist the balloons into shapes. Squirrels, dogs...horses..." Molly trailed off, distracted by the sparkly tiara she was trying on. Bill sighed. "I can barely tie my shoes, Molly! How am I supposed to make a giraffe from a balloon?" Molly rolled her eyes. "Fine, we'll get those twisty stick things that come in the party favor bags. You'll make stick giraffes. Easy as pie." Bill groaned. "This is the most ridiculous plan we've ever concocted." Molly grinned. "True, but you have to admit—it’s our most creative yet."
id
"gen-PcfHvlAGhcPQtXIalSt2pQIRYD2j"
total_cost
0.00026892
upstream_id
"8a5bbbaf66681587-SJC"
created_at
"2024-07-19T15:27:05.729249+00:00"
Friday, July 19th, 2024 at 3:27:05 PM GMT+00:00
model
"qwen/qwen-2-72b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Together"
latency
4475
moderation_latency
(null)
generation_time
0
finish_reason
"eos"
tokens_prompt
77
tokens_completion
248
native_tokens_prompt
83
native_tokens_completion
249
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00026892
Evaluation details
Result
Evaluator
Details
Meta Data
0.0848%
Matches word count
n/a
neededClean
false
words
171
0.0000%
Dialogue to Total Word Ratio
Ratio: 74.27%, Deviation: 24.27%
neededClean
false
wordsTotal
171
wordsDialogue
127
0.0424%