NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-07-19-01J35TCVYR1MTRRC01VR8DQATY
Run Details
Model:
WizardLM 2 8x22b
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
19.3s
Cost:
$0.000347
Provider:
DeepInfra
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
2.22%
Dialogue to Total Word Ratio
(details)
1.1117%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly cased the backyard, her eyes gleaming with mischief. "You sure this is the spot, Bill? Seems a bit... childish." Bill, stuffed into a too-small clown costume, adjusted his oversized bow tie. "Kid you not, Mol. Birthday parties are a goldmine. Parents spend a fortune on gifts these days." She smirked, plucking a rubber ducky from a nearby pool float. "And we're just gonna waltz in, grab the loot, and leave? What's the plan?" "Simple," Bill whispered, peering through a hedge at the unsuspecting children. "I'll distract 'em with some bad clowning, you swoop in, snatch the gifts, and we're out before they can say 'balloon animal.'" Molly raised an eyebrow. "Bad clowning? You mean your usual routine?" "Very funny," Bill deadpanned. "Just remember, we're not here to join the party. In and out, quick and silent." She grinned, tucking the duck under her arm. "Got it, boss. Silent but deadly, just like your jokes." "Ha ha," Bill said, unamused. "Just stick to the plan. And for the love of heists, don't eat the cake." Molly feigned innocence. "Who, me? Would I steal a bite of a kid's birthday cake?" "Yes, you," Bill said, pointing at her. "Last time, you got frosting on the getaway car's steering wheel." "Fine," Molly sighed. "No cake, no clowning around. Let's do this." Bill gave a nod, taking a deep breath. "Showtime." As he waddled toward the party, Molly muttered under her breath, "Break a leg, Bill. Preferably not mine."
id
"gen-O0TsihnTpcWRYO0Z7CNcW2HZEW0s"
total_cost
0.00034713
upstream_id
"cmpl-e8dd72531bc144b589219e33edb89a29"
created_at
"2024-07-19T15:40:20.393649+00:00"
7/19/2024, 3:40:20 PM
model
"microsoft/wizardlm-2-8x22b"
app_id
182717
streamed
false
cancelled
false
provider_name
"DeepInfra"
latency
19205
moderation_latency
(null)
generation_time
0
finish_reason
"stop"
tokens_prompt
95
tokens_completion
374
native_tokens_prompt
112
native_tokens_completion
439
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.00034713
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
246
2.22%
Dialogue to Total Word Ratio
Ratio: 63.97%, Deviation: 13.97%
neededClean
false
wordsTotal
247
wordsDialogue
158
1.1117%