NC Bench
Overview
About
Tests
Models
Model
Inflection 3 (PI)
Test
Dialogue tags
Scenario
Write 200 words with 90% dialogue
Run ID
2024-10-13-01JA2XR3X8JZ7R96AE21QB7FDX
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
**Scene** "Quiet, Bill!" Molly hissed, ducking behind a shrub. "Someone'll hear you." "Molly, we're in a park. It's not like the birthday boy's got spies hiding behind trees." "Don't be ridiculous," Molly snapped. "Of course he does. Who doesn't have spies at a children's party these days?" "Are you serious?" Bill groaned. "Look, let's just grab the presents and get out." "Not until I finish reciting my plan," Molly insisted. "Now, when we breach the pavilion, you'll grab the gifts while I distract the guests. I've prepared a special dance routine that'll knock their socks off." "Dancing? Molly, we're thieves, not entertainers." "We can be both, Bill! It's called multitasking." "Fine. But let's make it quick, okay? I don't want to end up in jail over some kid's tricycle." "Tricycle? Bill, haven't you heard? This party is for the son of the mayor. Imagine what he's getting!" "Alright, let's do it. But I'm telling you, Molly, if we get caught, I'm blaming your dance routine."
id
"gen-1728822661-VgtCPDSRkrvKUtiNRVOS"
total_cost
0.002685
cache_discount
(null)
created_at
"2024-10-13T12:31:15.863532+00:00"
Sunday, October 13th, 2024 at 12:31:15 PM GMT+00:00
model
"inflection/inflection-3-pi"
app_id
182717
streamed
true
cancelled
false
provider_name
"Inflection"
latency
5960
moderation_latency
(null)
generation_time
8219
finish_reason
(null)
tokens_prompt
68
tokens_completion
253
native_tokens_prompt
74
native_tokens_completion
250
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.002685
Evaluation details
Result
Evaluator
Details
Meta Data
0.0000%
Matches word count
n/a
neededClean
false
words
165
99.7977%
Dialogue to Total Word Ratio
Ratio: 92.12%, Deviation: 2.12%
neededClean
false
wordsTotal
165
wordsDialogue
152
49.8989%