Decision Making on MLGym Blotto
0.5ScoreHuman Best
Evaluation results
| Method | Links | |
|---|---|---|
| Human BestMethod Type=Human Baseline2026.06 | 0.5 | |
| ARTS*Base Model=Qwen 4B, Test-time trained=true2026.06 | 0.344 | |
| ARTSBase Model=Qwen 4B2026.06 | 0.251 | |
| MLEvolveMethod Type=Prior Works2026.06 | 0.25 | |
| ARTSBase Model=o32026.06 | 0.249 | |
| AIRAMethod Type=Prior Works2026.06 | 0.247 | |
| LinearMethod Type=Prior Works2026.06 | 0.076 |