Model

Phi-3.5 Mini 128k

Test

Dialogue tags

Scenario

Write 200 words with 90% dialogue

Run ID

2024-08-26-01J68D7B9MXXM3SNNCPRK5D1XQ

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

AI
Molly: "Alright, Bill, the plan is crystal. We hit the party at 10, blend in." Bill: "Ten. I'll clock in on the 'Happy Birthday to Bobby' song. Sprinkle a bit of that 'magic dust'." Molly: "Magic dust? You mean that glitter spray I picked up last week?" Bill: "Exactly. Once we're the crowd, I distract with a pop balloon. It’s classic!" Molly: "Easy for you to say. I’ll slice open that cake. Talk about cutting into a number of liabilities." Bill: "Marzipan layer. Perfect cover. Underneath, you nab the gifts." Molly: "Switch the Veggie Straws; don't scream!" Bill: "Veggie Straws. I remember now. Plus, kids love them. Ambiguous camouflage." Molly: "Foil capes. We'll run off like superheroes, nobody the wiser." Bill: "Imagine their faces—" Molly: "—when we pitch our capes, 'Fantastic Detectives, heroes on the loose!'" Bill: "Chuckle. All right, Molly. Heightened awareness. Gift theft mode starting at 10:05." Molly: "Got it! But if the dogs start barking at us, backflip to grocery store quickie." Bill: "Quickie, Molly. That's our escape route. Let's put our superhero capes on and fly." (The two thieves slip into the party, engaging the crowd, perfect timing strikes as they skillfully pilfer presents with superhero charm, exchanging scoffs and sly winks to one another.) (End of Scene)
id"gen-qHuUhFdbGCZyqtx81thOz2N9ie2z" 
total_cost0.000056
upstream_id"chat-7c3e1962fa154c20a22f08c9d9313a17" 
created_at"2024-08-26T22:34:49.169233+00:00" Monday, August 26th, 2024 at 10:34:49 PM GMT+00:00
model"microsoft/phi-3.5-mini-128k-instruct" 
app_id182717
streamedtrue
cancelledfalse
provider_name"Azure" 
latency149
moderation_latency(null)
generation_time11522
finish_reason"stop" 
tokens_prompt82
tokens_completion352
native_tokens_prompt84
native_tokens_completion476
num_media_prompt(null)
num_media_completion(null)
origin"https://ncbench.com/" 
usage0.000056

Evaluation details

Result Evaluator Details Meta Data
75.1556% Matches word count n/a
neededCleanfalse
words213
1.3359% Dialogue to Total Word Ratio
Ratio: 75.59%, Deviation: 14.41%
neededCleanfalse
wordsTotal213
wordsDialogue161
38.2458%