FinMMEval Task 2 Final Test Portal
📊
Submit multilingual financial QA answers for the FinMMEval test
Natural Language Processing, Machine Learning, and Computer Vision
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization
SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training
Submit multilingual financial QA answers for the FinMMEval test
Submit your Hindi benchmark predictions and see live rankings
Submit Arabic benchmark predictions and view live rankings
Submit predictions and view live leaderboard
Submit your JSON predictions and see real‑time leaderboard rankings