Prediction Market Betting on standardized 200-event shared subset
0.0008Brier Score GapGemini 3
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| Gemini 32026.07 | 0.0008 | 8.1 | 1.3 | -0.1 | 0.7 | 1.8 | -42.7 | |
| Claude Opus 4.62026.07 | 0.0016 | 22.1 | 5 | -14 | -3.5 | 10.9 | -99.9 | |
| GPT-5.2 (Base)2026.07 | 0.0347 | 4.5 | 2.4 | -14.9 | 1.9 | -0.1 | -99.9 | |
| LLaMA 4 Maverick2026.07 | 0.045 | -13.7 | -4.1 | -15.5 | -4 | -10 | -99.9 | |
| Grok 4.1 Fast2026.07 | 0.0462 | -11.6 | -7.8 | -26.4 | -7 | -6.3 | -99.9 |