FutureEval — leaderboard
Metaculus benchmark for AI forecasting accuracy on unresolved real-world questions across science, technology, health, geopolitics, AI, and other domains. Models make probabilistic forecasts and are ranked by a unified log-score-based forecasting score against community and pro forecaster baselines.
Metric: Unified Forecasting Score. Source: www.metaculus.com. Status: saturation imminent. 38 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 19.84 |
| 2 | Gemini 3.1 Pro (Preview) | 19.03 |
| 3 | Grok 4.20 Multi-Agent | 14.99 |
| 4 | Claude Opus 4.7 (High) | 14.62 |
| 5 | GPT-5.5 (High) | 14.06 |
| 6 | GPT-5.5 Instant | 13.84 |
| 7 | GPT-5.1 (High) | 12.14 |
| 8 | O3 | 11.94 |
| 9 | GPT-5 | 11.49 |
| 10 | GPT-5 (High) | 11.4 |
| 11 | Kimi K2.6 | 11.39 |
| 12 | Grok 4.3 (High) | 11.35 |
| 13 | GPT-5.4 (High) | 11.2 |
| 14 | Gemini 3 Pro | 10.57 |
| 15 | GPT-5.2 (High) | 10.55 |
Interactive version: theaggregate.ai/benchmark?slug=futureeval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.