Future Prediction on FUTUREX March 2026 Week 3 slice
71.43L1 ScoreMilkyway
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MilkywayBackbone=GPT-5.4, Official release status=true2026.04 | 71.43 | 82.26 | 63.05 | 45.85 | 60.9 | |
| MIROFLOWBackbone=GPT-5.4, Official release status=true2026.04 | 64.29 | 72.82 | 59.45 | 46.8 | 57.5 | |
| MEMEVOLVE+FLASH-SEARCHERBackbone=GPT-5.4, Official release status=false2026.04 | 64.2 | 63.12 | 48.8 | 35.93 | 48.06 | |
| AGENTKB+SMOLAGENTSBackbone=GPT-5.4, Official release status=false2026.04 | 63.4 | 61.73 | 47.2 | 34.51 | 46.65 | |
| FLASH-SEARCHERBackbone=GPT-5.4, Official release status=false2026.04 | 62.81 | 60.56 | 45.61 | 33.17 | 45.34 | |
| GPT-5.4 (with web search)Backbone=GPT-5.4, Official release status=false2026.04 | 62.14 | 59.8 | 44.24 | 31.57 | 44.07 |