FutureSearch BTF-2: leaderboard
FutureSearch Bench to the Future 2 pastcasting benchmark scored by Brier accuracy on resolved forecasting questions.
Metric: Brier Score. Source: evals.futuresearch.ai. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 0.13 | #63 |
| 2 | Gemini 3.1 Pro (Preview) | 0.14 | #58 |
| 3 | GPT-5.4 | 0.15 | #79 |
| 4 | Grok 4.20 | 0.17 | #175 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=futuresearch-btf-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.