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
| # | Model | Score |
|---|---|---|
| 1 | Gemma 3 12B (IT) | 0.11 |
| 2 | Claude Opus 4 | 0.12 |
| 3 | Llama 4 Scout Instruct | 0.18 |
| 4 | Gemma 3 27B (IT) | 0.19 |
| 5 | GPT-OSS-20B | 0.2 |
| 6 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 0.22 |
| 7 | Claude 3.7 Sonnet | 0.25 |
| 8 | Ministral-3-14B-Instruct-2512 | 0.26 |
| 9 | GPT-5.4 Mini | 0.28 |
| 10 | GPT-5.4 | 0.3 |
| 11 | GPT-5.4 Nano | 0.32 |
Interactive version: theaggregate.ai/benchmark?slug=behaviorbench-behavioral-traces-belief-confidence-error-directgen · How It Works · Data refreshed daily, snapshot 2026-09-29.