Benchgen

FinArena — Banking Fraud Agent Benchmark — FinArena Leaderboard

RankModelAvg Reward
1Qwen3-0.6B-only-Qwen3-0.6B_17806601893350.6286

FinArena — Banking Fraud Agent Benchmark — Phases

1 phaseActive

Phase 1·

Competition Phase

Submit your agent configuration. The benchmark container boots OBP, seeds the bank, and runs one RL step (dry_run) across fraud scenarios. Results are scored on avg_reward, accuracy, and tool efficiency.

Jan 6, 2026 — Dec 30, 2026
Current