OpenDataArena/ODA-Fin-RL-8B
Reinforcement Learning • 8B • Updated
AI & ML interests
Data-centric AI, LLM, MLLM
Recent Activity
Papers
Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets
OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
OpenDataArena/ODA-Fin-SFT-8B
Question Answering • 308k • Updated
• 11 • 1
OpenDataArena/MMFineReason-4B
Visual Question Answering • Updated
• 50 • 14
OpenDataArena/MMFineReason-2B
Visual Question Answering • 2B • Updated
• 10 • 8
OpenDataArena/MMFineReason-8B
Visual Question Answering • 9B • Updated
• 72 • 10
OpenDataArena/Qwen3-8B-ODA-Math-460k
Text Generation • 308k • Updated
• 7 • 1
OpenDataArena/Qwen2.5-7B-ODA-Math-460k
Text Generation • 8B • Updated
• 2
OpenDataArena/Qwen3-8B-ODA-Mixture-100k
Text Generation • 308k • Updated
• 50 • 1
OpenDataArena/Qwen3-8B-ODA-Mixture-500k
Text Generation • 308k • Updated
• 17
OpenDataArena/Qwen2.5-7B-ODA-Mixture-100k
Text Generation • 333k • Updated
• 9
OpenDataArena/Qwen2.5-7B-ODA-Mixture-500k
Text Generation • 333k • Updated
• 20 • 2