BehaviorBench (Behavioral Traces) - Trade Amount Error (DirectGen): leaderboard

Metric: Median absolute error of the predicted trade amount (paper units, unbounded); history interface DirectGen (the target wallet's most recent visible history, up to 30 events for Belief); 2,000 pseudonymous prediction-market wallets reconstructed from public Polymarket metadata and Polygon on-chain logs, about 59,560 chronologically held-out test transactions; unparsable outputs count as failures; context-only baseline 31.79; lower is better. Source: arxiv.org. Saturation forecast: Around June 2027. 11 models tracked.

Top models

#ModelScore
1Gemma 3 12B (IT)8.34
2Gemma 3 27B (IT)9
3Llama 4 Scout Instruct9.14
4Claude 3.7 Sonnet9.49
5GPT-5.49.63
6GPT-5.4 Mini9.8
7NVIDIA-Nemotron-3-Nano-30B-A3B-BF169.95
8GPT-OSS-20B10.4
9GPT-5.4 Nano11.37
10Claude Opus 412.47
11Ministral-3-14B-Instruct-251221.99

Interactive version: theaggregate.ai/benchmark?slug=behaviorbench-behavioral-traces-trade-amount-error-directgen · How It Works · Data refreshed daily, snapshot 2026-09-29.