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. Saturation forecast: Estimated already saturated. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.6 | 0.95 | #26 |
| 2 | Claude Fable 5 | 0.95 | #16 |
| 3 | GPT-5.6 Sol | 0.95 | #19 |
| 4 | Gemini 3.1 Pro (Preview) | 0.95 | #58 |
| 5 | DeepSeek V4 Pro (0813) | 0.95 | #53 |
| 6 | Gemini 3.8 Flash | 0.95 | #21 |
| 7 | Claude Opus 5.5 | 0.95 | #3 |
| 8 | Claude Fable 5.1 | 0.95 | #9 |
| 9 | GPT-6 Astra | 0.95 | #6 |
| 10 | GLM-5.3 | 0.95 | #39 |
| 11 | GPT-6.1 Sol | 0.95 | #7 |
| 12 | Kimi K3 | 0.95 | #30 |
| 13 | DeepSeek V4.1 Flash | 0.94 | #36 |
| 14 | GPT-6 Luna | 0.94 | #56 |
| 15 | Hy3 | 0.94 | #93 |
No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=prophetarena · How It Works · Data refreshed daily, snapshot 2026-10-20.