NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-23-01J3G8118BRBB97625BSMTDRKS
Run Details
Model:
Llama 3.1 70B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
3.1s
Cost:
$0.000287
Provider:
Fireworks
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
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
The sweet aroma of freshly baked bread wafted through the air, mingling with the soft hum of conversation in the cozy bakery. Flour dusted the countertops, and the soft glow of golden lighting made everything feel warm and inviting. "I'm telling you, I saw him arguing with the mayor just last night." "At the town hall meeting?" "No, at the diner. They were in the back booth, trying to keep their voices down, but I could tell it was intense. The mayor's face was red as a tomato." "That's not surprising, given the plans for the new development. I've heard the mayor is pushing for it big time." "Yeah, and I know why. He's got a stake in the project, doesn't he?" "That's what I've heard. But I'm sure he'll deny it to his grave." The baker slid a tray of golden-brown croissants into the display case, the sound of gentle clinking filling the air. "I just hope it doesn't all come crashing down, like the last time we had a big project in town." "Me too. We can't afford to lose any more businesses. This town is barely holding on as it is."
id
"gen-NVBB9aybRpcOXpZEyhUpTakLVQRJ"
total_cost
0.0002871
upstream_id
"497a5511-71cc-4517-9b9e-ed1627c5ccb6"
created_at
"2024-07-23T16:50:40.887587+00:00"
7/23/2024, 4:50:40 PM
model
"meta-llama/llama-3.1-70b-instruct"
app_id
182717
streamed
false
cancelled
false
provider_name
"Fireworks"
latency
2948
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
103
tokens_completion
246
native_tokens_prompt
71
native_tokens_completion
248
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0002871
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)