Loading
AIcrowd
Challenges
Organize a challenge FAQ Contact
Log In Sign Up
0 Follower
0 Following
budai

Location

HK

Badges

2
1
0

Connect

Activity

May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Mon
Wed
Fri

Challenge Categories

Loading...

Challenges Entered

Completed
Orak Game Agent Challenge 2025
By Krafton AI

Build an LLM agent for five real-world games

Latest submissions

No submissions made in this challenge.
Completed
Flextrack Challenge 2025
By University of Wollongong

Detecting Energy Flexibility in Buildings

Latest submissions

See All
failed 297692
graded 294217
graded 294153
Completed
Commonsense Persona-Grounded Dialogue Challenge 2025
By Sony Group Corporation

Create Context-Aware, Dynamic, and Immersive In-Game Dialogue

Latest submissions

See All
failed 288545
graded 288333
graded 288332
Completed
Meta CRAG - MM Challenge 2025
By Meta

Improve RAG with Real-World Benchmarks | KDD Cup 2025

Latest submissions

No submissions made in this challenge.
Starting soon
Multi-Agent Reinforcement Learning for Iterative Reasoning
By Strategic Intelligence for Machine Agents (SIGMA) Lab

Latest submissions

No submissions made in this challenge.
Completed
Context-Aware Dialogue (Task 2)
By Sony Group Corporation

Build Context-Aware Conversational NPC Agents

Latest submissions

See All
graded 288333
graded 288285
graded 288283
Completed
Task-Oriented Dialogue (Task 1)
By Sony Group Corporation

Task-Oriented Conversational AI for NPC Agents

Latest submissions

See All
graded 288332
graded 288284
graded 288282
Completed
Integrating Contextual Dialogue and Task Execution (Hybrid)
By Sony Group Corporation

Context-Aware & Task-Driven NPC Agents

Latest submissions

See All
failed 288545
graded 288326
failed 288323
Participant Rating
Participant Rating
  • budai Commonsense Persona-Grounded Dialogue Challenge 2025
    View

Commonsense Persona-Grounded Dialogue Chall-0431ae

Regarding the final ranking method

10 months ago

Hi,

I have two questions regarding the final ranking method, may I seek for clarification?

  1. In API track, token limit are stated in the API Usage Constraints section. However, I think code can be submitted and pass even if the token limit are exceeded. Will token usage be considered in the final ranking?
  • Input token limit per turn : 2,000 tokens
  • Output token limit per turn : 200 tokens
  1. Are all submissions be used in final ranking or just the submission with highest score be considered?

Thanks

budai has not provided any information yet.