NC Bench
Overview
About
Tests
Models
Model
AI21 Jamba 1.5 Mini
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-08-26-01J6894Y3A8DSWPEX56W6ZZEEN
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
"Alright, Bill, here's the plan," Molly whispered, eyes scanning the crowded playground. "We blend in with the parents, casual-like. No one suspects a thing." Bill adjusted his fake mustache and gave a thumbs-up. "Blending in, you say? I gotcha. Like a chameleon in a bowl of fruit loops." Molly chuckled. "Exactly. Now, once we're inside, we keep our eyes peeled for the presents. They're usually stashed somewhere out of the way, but accessible enough for cake time." "Gotcha. So, we waltz in, grab the loot, and waltz out," Bill said, winking. "Simple as pie." "Not so fast. We need a distraction. A good one," Molly cautioned. "Think kid-friendly. What do kids love more than anything?" Bill snapped his fingers. "Balloons! We set off a bunch of them near the entrance. Everyone rushes to see the commotion, and we slip out the back." Molly nodded. "Perfect. And remember, no huffing helium this time. Last thing we need is you talking like Donald Duck."
id
"gen-iJCdqdCtXzvLzGhdoQ9lDtcvs6YZ"
total_cost
0.000122
upstream_id
"chat-31a961a2c4b945cc88d0abaad7fa7153"
created_at
"2024-08-26T21:23:27.543725+00:00"
Monday, August 26th, 2024 at 9:23:27 PM GMT+00:00
model
"ai21/jamba-1-5-mini"
app_id
182717
streamed
true
cancelled
false
provider_name
"AI21"
latency
551
moderation_latency
(null)
generation_time
2685
finish_reason
"stop"
tokens_prompt
68
tokens_completion
239
native_tokens_prompt
80
native_tokens_completion
265
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000122
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
164
62.3185%
Dialogue to Total Word Ratio
Ratio: 81.71%, Deviation: 8.29%
neededClean
false
wordsTotal
164
wordsDialogue
134
31.1593%