BehaviorBench (Behavioral Traces) - Belief Choice (DirectGen): leaderboard

Metric: Choice accuracy (%): predicted final revealed side (YES or NO) of the wallet in the target market; 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, 22,204 chronologically held-out wallet-market test instances; chance 50, context-only baseline 53.13; higher is better. Source: arxiv.org. Saturation forecast: Around December 2027. 11 models tracked.

Top models

#ModelScore
1GPT-5.470.75
2Claude Opus 470.22
3Gemma 3 12B (IT)70.21
4Gemma 3 27B (IT)70.08
5Claude 3.7 Sonnet67.68
6GPT-5.4 Mini66.34
7GPT-OSS-20B66
8GPT-5.4 Nano65.8
9Llama 4 Scout Instruct64.77
10Ministral-3-14B-Instruct-251259.82
11NVIDIA-Nemotron-3-Nano-30B-A3B-BF1658.63

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