ProphetArena — leaderboard
Live forecasting benchmark testing LLMs on real-world prediction tasks from Kalshi markets. Models assign probabilistic estimates; scored by 1-Brier (higher is better). Tests calibration and world knowledge.
Metric: 1 - Brier Score. Source: www.prophetarena.co. Status: saturated. 50 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 0.95 |
| 2 | GPT-5.5 (High) | 0.95 |
| 3 | Claude Opus 4.8 (Thinking) | 0.95 |
| 4 | Gemini 3.5 Flash | 0.95 |
| 5 | Grok 4.20 | 0.95 |
| 6 | GLM-5.1 | 0.94 |
| 7 | Claude Sonnet 4.6 | 0.94 |
| 8 | DeepSeek V4 Pro | 0.94 |
| 9 | Kimi K2.5 | 0.94 |
| 10 | Grok 4.3 | 0.94 |
| 11 | MiniMax-M2.7 | 0.94 |
| 12 | Qwen 3.6 Plus | 0.94 |
| 13 | Kimi K2.6 | 0.94 |
| 14 | Gemini 3 Flash (Preview) | 0.93 |
| 15 | Gemini 3 Pro (Preview) | 0.91 |
Interactive version: theaggregate.ai/benchmark?slug=prophetarena · How the rankings work · Data refreshed daily, snapshot 2026-07-22.