BehaviorBench (Behavioral Traces) - Belief Confidence Error (ProfileGen): leaderboard

Metric: Confidence mean absolute error on a 0 to 1 scale: gap between the predicted and revealed share of the final position held on the dominant side; history interface ProfileGen (a released structured profile summarizing the wallet's pre-target behavior); 2,000 pseudonymous prediction-market wallets reconstructed from public Polymarket metadata and Polygon on-chain logs, 22,204 chronologically held-out wallet-market test instances; context-only baseline 0.3417; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.

Top models

#ModelScore
1Claude 3.7 Sonnet0.08
2Claude Opus 40.08
3Gemma 3 12B (IT)0.08
4Gemma 3 27B (IT)0.09
5GPT-OSS-20B0.1
6GPT-5.4 Mini0.13
7Llama 4 Scout Instruct0.13
8GPT-5.4 Nano0.15
9GPT-5.40.18
10Ministral-3-14B-Instruct-25120.19
11NVIDIA-Nemotron-3-Nano-30B-A3B-BF160.2

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