NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35T84PRZHQKE3536XYYTQ1P
Run Details
Model:
Claude 3 Haiku
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.1s
Cost:
$0.000387
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
7.1507%
Overall
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
"Alright, Molly, here's the plan," Bill whispered, hunched over the blueprints of the house. "We hit the place during the birthday party, while all the kids are distracted by the clown and the piƱata." Molly nodded, a mischievous grin spreading across her face. "Perfect. And what about the security system?" "Piece of cake," Bill replied, tapping the blueprint. "We go in through the back door, disable the alarm, and make a beeline for the living room. That's where they'll have all the presents stashed." "And the getaway?" Molly asked, arching an eyebrow. "Van's parked around the corner, engine running. We grab the loot and disappear before anyone even knows what hit 'em," Bill said, a triumphant gleam in his eyes. Molly chuckled, rubbing her hands together. "I love it when a plan comes together. This is gonna be our biggest heist yet, Bill." "You bet, kid," Bill said, clapping Molly on the back. "Those presents are as good as ours." The two thieves exchanged a conspiratorial look, already imagining the piles of wrapped gifts they'd soon be hauling away.
id
"gen-z2TsSVU0aKM3e8Y8FQed0GOun74f"
total_cost
0.0003875
upstream_id
"msg_01UnK2M1JrMJEuMs8hCjXvQY"
created_at
"2024-07-19T15:37:29.219683+00:00"
7/19/2024, 3:37:29 PM
model
"anthropic/claude-3-haiku:beta"
app_id
182717
streamed
false
cancelled
false
provider_name
"Anthropic"
latency
2988
moderation_latency
(null)
generation_time
0
finish_reason
"end_turn"
tokens_prompt
68
tokens_completion
247
native_tokens_prompt
75
native_tokens_completion
295
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.0003875
Evaluation details
Result
Evaluator
Details
Meta Data
14.30%
Matches word count
n/a
neededClean
false
words
179
0.00%
Dialogue to Total Word Ratio
Ratio: 62.01%, Deviation: 27.99%
neededClean
false
wordsTotal
179
wordsDialogue
111
7.1507%