Model

Qwen 2 72B

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-07-19-01J35T85M1W8WETNYZTM0K7HPP

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

AI
: Molly whispered, "So, we just waltz in, grab the loot, and vamoose?" Bill smirked, "Loot? More like My Little Ponies and Paw Patrol pjs. But yeah, that’s the gig." "Bill, this is low, even for us," Molly said, shaking her head. He shrugged. "I know, but think of the resale value. Desperate parents, Christmas around the corner. We're doing them a favor, really." "Right. A favor," Molly muttered. "And what if we get caught?" "Ah, that's the genius part. We blend in. Face paint, clown noses, the works. Who's going to suspect the funny guys?" Molly sighed. "You planned this all out, didn't you?" Bill grinned. "Of course. It's not my first rodeo, remember?" "But it is my first kiddie heist. Don’t you have something less...less Christmas?" Bill sighed, "Look, it’s either this or the senior bingo night. Your pick." Molly rolled her eyes. "Fine, but I'm not wearing a tutu." Bill chuckled. "Deal. We'll stick to the oversized clown shoes and rainbow wigs. Professional, yet festive."
id"gen-fylbk4f0hB4LhqetYjNhkbZ0jquu" 
total_cost0.0003114
upstream_id"17ee101d-49b5-4a8f-a1b2-4eed0ab9fbaf" 
created_at"2024-07-19T15:37:30.798001+00:00" Friday, July 19th, 2024 at 3:37:30 PM GMT+00:00
model"qwen/qwen-2-72b-instruct" 
app_id182717
streamedfalse
cancelledfalse
provider_name"Fireworks" 
latency3374
moderation_latency(null)
generation_time0
finish_reason"stop" 
tokens_prompt77
tokens_completion263
native_tokens_prompt82
native_tokens_completion264
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.0003114

Evaluation details

Result Evaluator Details Meta Data
0.0007% Matches word count n/a
neededCleanfalse
words167
91.3993% Dialogue to Total Word Ratio
Ratio: 84.52%, Deviation: 5.48%
neededCleanfalse
wordsTotal168
wordsDialogue142
45.7000%