NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 8B
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-07-23-01J3G80V1CTWBYJXR7E3C9Y1HQ
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 leaned against the wall, pencil tucked behind her ear as she studied the layout of the party's venue. Bill paced back and forth, his loud whisper echoing off the deserted office space they'd commandeered. "I'm telling you, Molly, we can't go in looking like we're trying to rob a bank. Kids' parties are about flashing lights and princess dresses. We need to blend in." "What, like a pair of children? There's a reason I didn't take that gig with the clown makeup." "Hey, that clown job had real potential. I figured it'd be a solid alias. 'Binky the Birthday Clown' – what could go wrong?" "It could go very wrong. The birthday boy might still be traumatized from your last clown gig. Remember when you lost control of the squirt gun and drenched the mayor's kid?" Bill stopped pacing, flashing her a mock-offended look. "That was one time, and I was young. I've been studying the art of innocuous clownery since." Molly raised an eyebrow, still scribbling notes on her pad. "I'm not sure 'art' is the word I'd use when someone in a curly wig makes balloon animals with what looks suspiciously like escaped tarantulas." Bill's grin returned, and he clapped Molly on the back. "That was an homage, Molly. To the surrealist masters. Next thing you know, you'll be accusing me of trying to 'ironize the concept of trauma through hosiery.'" Molly shook her head, pencils stuck between her teeth, eyes fixed on the layout. "Let's focus on not getting caught, Bill. We can save the surrealist critique for the getaway."
id
"gen-G2ggejY6mRlOhleR342XTSa40l4L"
total_cost
0.0000848
upstream_id
"a96b0f3b-9a06-48ce-a968-a165c1d9cd05"
created_at
"2024-07-23T16:50:32.843541+00:00"
Tuesday, July 23rd, 2024 at 4:50:32 PM GMT+00:00
model
"meta-llama/llama-3.1-8b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
1303
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
102
tokens_completion
352
native_tokens_prompt
70
native_tokens_completion
354
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0000848
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
264
0.0000%
Dialogue to Total Word Ratio
Ratio: 70.45%, Deviation: 19.55%
neededClean
false
wordsTotal
264
wordsDialogue
186
0.0000%