NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-14-01J2SKDYN2XXNER0VQCXGKGCGH
Run Details
Model:
GPT-4o, May 13th (temp=1)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
5.6s
Cost:
$0.004960
Provider:
OpenAI
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
"Did you notice anything odd about Mr. Whitmore lately?" "Odd? Like what?" "Well, just this morning he asked for an almond croissant, but you know Mr. Whitmore always takes a plain scone." "Maybe he wanted to try something different." "Doubtful. He's been sticking to that plain scone for twenty years. Folks don't change overnight." "Could be he just fancied a change. People do that sometimes." "But then there was his hat. He never wears a hat, especially not indoors. Today, there he was with a broad-brimmed Panama hat. Oddest thing." "You're right; that is peculiar. You think it means something?" "I don't know, but it's worth keeping an eye on. Where there's smoke, there's usually fire." "So what are you suggesting? That we follow him?" "No, heavens no, but I do think we should be more observant. Notice if he starts behaving differently again." "And if he does?” "Then we bake him a batch of his favorite scones and ask him what's going on." "Isn't that a bit forward? People might think we're being nosy." "Maybe, but in a town this small, everyone’s business is everyone’s business. Sometimes, nosy saves lives. Or at least clears up mysteries." "I suppose we could offer him one of those new raspberry scones we’ve been perfecting as well." "Now that’s an idea. It might just butter him up enough to spill the beans."
id
"gen-EBJLnoBcXn25eotoJ45VWPE7eEPE"
total_cost
0.00496
upstream_id
"chatcmpl-9l1LwrqGIuyHIxCfgWvJFQ90j1mni"
created_at
"2024-07-14T21:47:28.907606+00:00"
7/14/2024, 9:47:28 PM
model
"openai/gpt-4o-2024-05-13"
app_id
182717
streamed
false
cancelled
false
provider_name
"OpenAI"
latency
4588
moderation_latency
215
generation_time
0
finish_reason
"stop"
tokens_prompt
69
tokens_completion
318
native_tokens_prompt
68
native_tokens_completion
308
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00496
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)