NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-09-20-01J881C3HGFP9WD0RRF2N7FSER
Run Details
Model:
Qwen 2.5 72B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
7.2s
Cost:
$0.000122
Provider:
Hyperbolic
Evaluation summary
Score
Evaluator
Details Link
13.53%
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 warm scent of cinnamon and freshly baked bread filled the cozy bakery. Sunlight streamed through the window, casting a golden glow on the display case where an array of pastries glistened. "It's been ages since I had one of these,"
a voice said
, fingers hovering over a cream-filled éclair. " Memories of my grandmother's kitchen come flooding back." "Same here,"
another voice chimed in
, reaching for a glazed donut. "But I think I'll stick to something a bit less sinful today. Maybe a scone?" "Good choice. They're homemade, you know. The lady behind the counter swears by her grandmother's recipe." "Really? I'll have to try one then. What’s your go-to order here?" "A blueberry muffin and a cappuccino. Can't go wrong with that combination. Especially on a day like this." "Sounds perfect. I might just join you, if you don’t mind." "Not at all. The more, the merrier. Plus, the company makes the coffee taste even better."
id
"gen-nKePCo8KvzyGjsjcL7zhLQGmNRIS"
total_cost
0.0001216
upstream_id
"chat-b16f77264c2645308b7e4ea2089fbeb7"
created_at
"2024-09-20T15:39:01.310161+00:00"
9/20/2024, 3:39:01 PM
model
"qwen/qwen-2.5-72b-instruct"
app_id
182717
streamed
true
cancelled
false
provider_name
"Hyperbolic"
latency
560
moderation_latency
(null)
generation_time
6345
finish_reason
"stop"
tokens_prompt
79
tokens_completion
219
native_tokens_prompt
83
native_tokens_completion
221
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0001216
Evaluation details
Result
Evaluator
Details
Meta Data
13.53%
Count dialogue tags
n/a
neededClean
false
dialogueTags
0
"a voice said"
1
"another voice chimed in"