BehaviorBench (Behavioral Traces) - Belief Confidence Error (DirectGen): 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 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; context-only baseline 0.3417; lower is better. Source: arxiv.org. Saturation forecast: Around December 2026. 11 models tracked.

Top models

#ModelScore
1Gemma 3 12B (IT)0.11
2Claude Opus 40.12
3Llama 4 Scout Instruct0.18
4Gemma 3 27B (IT)0.19
5GPT-OSS-20B0.2
6NVIDIA-Nemotron-3-Nano-30B-A3B-BF160.22
7Claude 3.7 Sonnet0.25
8Ministral-3-14B-Instruct-25120.26
9GPT-5.4 Mini0.28
10GPT-5.40.3
11GPT-5.4 Nano0.32

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