NC Bench
Overview
About
Tests
Models
Model
Liquid: LFM 40B MoE
Test
Dialogue tags
Scenario
Write 500 words with 30% dialogue
Run ID
2024-10-01-01J94R3ESHQT16AJSCJWC98R8A
Model input
User/Human
You are a author of comedic heist books. Please write a 500 word scene that has 30% 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
—So, Bill, here's how we're going to do it. We'll scope out this house a few days ahead of time and figure out the kid's schedule. What time the party starts. What time the presents being revealing A? Can we just steal it then? —If only it were that easy, Molly. No, we can't steal the presents right in front of the children during the party. We'd get caught for sure. We'll need to wait for the party to end and the kids to leave. That'll give us the opportunity to take the presents without the risk of being caught. —Fine. But you must promise me this. Once we're inside that house, I want no talking. None of those awkward silences that always come when people are too scared to talk. You know the type B I want total silence except for whatever instructions you might need to give me. —Alright. No talking at all, and just in case you get nervous or something else prevents you from being able to hear me, I'll also give you hand signals A We'll agree on what each one means before the job.
id
"gen-1727810092-vKFRjvGHTgR0EdGXE5gL"
total_cost
0
upstream_id
"chatcmpl-9182ed21-bd08-4bd9-ac6c-f5600e96abdd"
created_at
"2024-10-01T19:14:54.507025+00:00"
Tuesday, October 1st, 2024 at 7:14:54 PM GMT+00:00
model
"liquid/lfm-40b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Lambda"
latency
63
moderation_latency
(null)
generation_time
2205
finish_reason
"stop"
tokens_prompt
95
tokens_completion
230
native_tokens_prompt
135
native_tokens_completion
294
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
190
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 30.00%
neededClean
false
wordsTotal
190
wordsDialogue
0
0.0000%