NC Bench
Overview
About
Tests
Models
Model
EVA Qwen 2.5 14B
Test
Dialogue tags
Scenario
Write 200 words with 50% dialogue
Run ID
2024-10-01-01J94RPM00KQDXQJE1247TT43H
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 and Bill pored over a detailed floorplan of the sprawling mansion. Molly: "Alright, Bill. This party's happening tonight. How do we get in?" Bill: "Simple. I'll sneak out of the kitchen window. The caterers are packed in there like sardines anyway." Molly: "And then?" Bill: "Then I'll make my way to the nursery. Ruin the day for some bratty kid." Molly: "That seems a bit harsh, don't you think? We're thieves, not joy-stealers." Bill: "Look, all I see are presents. Dolls, trucks, gadgets. A dollar sign on any of it." Molly: "I see something else: parents who have no idea what a disappointment their lives are. What the fuck." Bill: "You, Molly, have issues." Molly: "Got any angles on alarms?" Bill: "They've gone all out. G4 monitoring, thermal sensors. It's a fire pit." Molly: "Then I suppose I'll have to go old school." Bill: "You working any magic putty this time?" Molly: "Definitely the magic putty. I'm aging out of this line of work." Bill: "You really expect a smooth getaway with you carrying a bundle full of teddy bears?" Molly: "Do you have any better ideas, or are you just here to complain?" Bill: "...Just making sure we're all on the same page. I'll start in the kitchen."
id
"gen-1727810719-zqKY8N7KovNdV1PZgqhs"
total_cost
0.000177
upstream_id
"chatcmpl-3facede6-72dc-49fa-8e53-aa3a36c21991"
created_at
"2024-10-01T19:25:50.376767+00:00"
Tuesday, October 1st, 2024 at 7:25:50 PM GMT+00:00
model
"eva-unit-01/eva-qwen-2.5-14b"
app_id
182717
streamed
true
cancelled
false
provider_name
"Infermatic"
latency
1601
moderation_latency
(null)
generation_time
28692
finish_reason
"stop"
tokens_prompt
67
tokens_completion
318
native_tokens_prompt
72
native_tokens_completion
318
native_tokens_reasoning
(null)
num_media_prompt
(null)
num_media_completion
(null)
origin
"https://ncbench.com/"
usage
0.000177
Evaluation details
Result
Evaluator
Details
Meta Data
86.3803%
Matches word count
n/a
neededClean
false
words
211
0.0000%
Dialogue to Total Word Ratio
Ratio: 86.73%, Deviation: 36.73%
neededClean
false
wordsTotal
211
wordsDialogue
183
43.1902%