NC Bench
Overview
About
Tests
Models
Model
AI21 Jamba 1.5 Large
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-26-01J6897A4TGGCBR8HKA7KAHWA9
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: Here's the plan, Bill. We sneak in during the cake cutting. Bill: Genius! Everyone will be distracted by the sugar rush. Molly: Exactly. We slip in, grab the loot, and slip out. Easy peasy. Bill: What about the kids? They're small, but they can scream bloody murder. Molly: We'll wear disguises. Clown costumes. Bill: Clowns? Seriously? Molly: Trust me, no one will suspect a thing. Plus, we'll blend right in. Bill: Fine, but if I get a pie in the face, I'm blaming you. Molly: Deal. Now, about the escape route... Bill: We could use the bouncy castle as a trampoline. Molly: Brilliant! We bounce over the fence and vanish into the night. Bill: What if someone sees us? Molly: We'll leave a trail of candy leading the other way. Bill: Distraction and misdirection. I like it. Molly: Just remember, Bill, no sampling the candy. Bill: Hey, I'm a professional. I know the rules. Molly: Good. Let's go over the layout one more time...
id
"gen-Uwc1lbsNwAOy2JEiSRjYlgE2EqNm"
total_cost
0.002472
upstream_id
"chat-fedc863fd8294c20b1333f7522ca84a4"
created_at
"2024-08-26T21:24:53.162908+00:00"
Monday, August 26th, 2024 at 9:24:53 PM GMT+00:00
model
"ai21/jamba-1-5-large"
app_id
182717
streamed
true
cancelled
false
provider_name
"AI21"
latency
811
moderation_latency
(null)
generation_time
10326
finish_reason
"stop"
tokens_prompt
68
tokens_completion
248
native_tokens_prompt
80
native_tokens_completion
289
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.002472
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
165
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
165
wordsDialogue
0
0.0000%