Probability Forecasting on Paleka + Polymarket partition slice N=2412 (combined)
0.2485B2 Scoremeta_llama-3.3-70b-versatile
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| meta_llama-3.3-70b-versatileModel=meta_llama-3.3-70b-versatile2026.05 | 0.2485 | 0.2404 | 0.2406 | 0.212 | 0.21 | -0.0079 | -0.0385 | |
| openai_gpt-5.4-nanoModel=openai_gpt-5.4-nano2026.05 | 0.2356 | 0.2212 | 0.2209 | 0.2015 | 0.1989 | -0.0148 | -0.0367 | |
| openai_gpt-5.4-miniModel=openai_gpt-5.4-mini2026.05 | 0.2261 | 0.2112 | 0.2111 | 0.1886 | 0.1827 | -0.015 | -0.0435 | |
| anthropic_claude-haiku-4-5-20251001Model=anthropic_claude-haiku-4-5-202510012026.05 | 0.1975 | 0.1931 | 0.1909 | 0.1643 | 0.1631 | -0.0066 | -0.0344 |