NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2024-08-26-01J68CZY0F9WNES4E3T7TRHE2V
Run Details
Model:
Hermes 3 405B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
24.1s
Cost:
$0.000000
Provider:
Lambda
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 10% 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 and Bill, dressed in black, crouched behind a large inflatable bounce house, eyeing the pile of brightly wrapped presents. "Okay, here's the plan," Molly whispered. "I'll create a distraction while you sneak in and grab the presents." Bill nodded, a mischievous glint in his eye. "What kind of distraction?" Molly grinned. "I'll let loose a dozen squirrels in the party area. That should cause enough chaos for you to get in and out unnoticed." "Brilliant!" Bill chuckled. "But won't the kids love the squirrels even more than the presents?" "Exactly!" Molly said, rubbing her hands together. "They'll be so preoccupied with the furry little critters, they won't even notice the presents are gone until it's too late." The two thieves high-fived each other, stifling their laughter. Suddenly, the sound of children's laughter and playful screams filled the air as the party kicked into full swing. "Alright, it's showtime," Molly said, pulling out a cage full of squirrels from her backpack. "Let's give these kids a birthday they'll never forget... and score some sweet loot while we're at it!"
id
"gen-qSBnqzyPB2iL07BCj8QPP79wzIY2"
total_cost
0
upstream_id
"chatcmpl-64719fe8-518a-4f07-a28e-04108ea97534"
created_at
"2024-08-26T22:30:58.501094+00:00"
8/26/2024, 10:30:58 PM
model
"nousresearch/hermes-3-llama-3.1-405b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Lambda"
latency
7938
moderation_latency
(null)
generation_time
16024
finish_reason
"stop"
tokens_prompt
67
tokens_completion
252
native_tokens_prompt
83
native_tokens_completion
253
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0
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: 55.00%, Deviation: 45.00%
neededClean
false
wordsTotal
180
wordsDialogue
99
7.1507%