NC Bench
Overview
About
Tests
Models
Model
Llama 3.1 405B
Test
Dialogue tags
Scenario
Write unattributed dialogue
Run ID
2024-07-23-01J3G4ZH4G6X7TCWCMZE4566GH
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
Flour dusted the air as the mixer whirred to life, its sweet melody filling the cozy bakery. The scent of freshly baked croissants wafted from the oven, making stomachs growl with anticipation. "I swear, I don't know how you do it, but these smell even better than usual." "Thanks, I think it's the new butter we're using. It gives them a richer flavor." "I'll have to take a few dozen home to Tom. He's been stressing about the upcoming festival, and a little pastry therapy is just what he needs." "Ha! Well, I'm happy to help. We should make some special festival treats, too. Maybe some sugar cookies with the town's logo on them?" "That's a great idea! I can see it now: 'Welcome to Oakwood' in icing letters. We'll be the talk of the festival." As the mixer continued to whir, a sudden jolt shook the bakery. The lights flickered and the oven sputtered. "What on earth...? It sounds like something exploded in the back room."
id
"gen-tectsMPqkbDA4MzodbUuiSYl3ogL"
total_cost
0.000894
upstream_id
"0fc32c59-60e9-49e2-89a2-d3b5b63f5fd3"
created_at
"2024-07-23T15:57:31.459173+00:00"
Tuesday, July 23rd, 2024 at 3:57:31 PM GMT+00:00
model
"meta-llama/llama-3.1-405b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
8676
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
103
tokens_completion
225
native_tokens_prompt
71
native_tokens_completion
227
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000894
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)