| Rank | Author | Strategy | Elo | Win% | Kill% | Attempts |
|---|---|---|---|---|---|---|
Program an AI agent that outmaneuvers opponents in aerial combat. Upload an ONNX model that observes the battlefield and decides actions in real time.
Your model receives a 224-dimensional observation and outputs 3 continuous actions each tick. It plays 100 matches against other submissions and is scored by Elo rating. Elimination wins count more than HP wins. Check out the GitHub repo to get started.
Results from the Aug 27, 2026 tournament
| Placement | Author | Strategy | Rounds Won | Win % | Seed |
|---|---|---|---|---|---|
| #1 | @YondonFu | VibePilotV9 | 4 | 71.2% | #2 |
| #2 | @josusanmartin | p80_hg_a465 | 4 | 59.4% | #21 |
| #3 | @drCathieSo_eth | Harrier | 3 | 72.5% | #3 |
| #4 | @0xStonks | celeritas | 3 | 62.1% | #23 |
| #5 | @cameronspirals | lazarus-xi | 2 | 65.6% | #9 |
| #6 | @samaltman43 | best | 2 | 62.2% | #22 |
| #7 | @Marcello_AI | marcello_lead | 2 | 60.4% | #4 |
| #8 | @Virtuvest6 | Virtu-C15 | 1 | 52.4% | #1 |
| #9 | @onblueroses | testing123 | 1 | 64.8% | #16 |
| #10 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | 1 | 59.7% | #15 |
Strategies ranked by cross-play Elo. Ratings start provisional (vs reference pool) and refine via head-to-head Swiss rounds every 30 minutes.
| Rank | Author | Strategy | Elo | Attempts | Last Submitted |
|---|---|---|---|---|---|
| #1 | Baseline Strategy | Starter | 1000 | — | — |
| #2 | @Virtuvest6 | Virtu-C15 | -5890~ | 18 | 2d ago |
| #3 | @YondonFu | VibePilotV9 | -6063~ | 9 | 19d ago |
| #4 | @drCathieSo_eth | Harrier | -6087~ | 16 | 12d ago |
| #5 | @Marcello_AI | marcello_lead | -6177~ | 28 | 29d ago |
| #6 | @m_scalar | msc_25 | -6192~ | 196 | 29d ago |
| #7 | @moor41495 | moor_24 | -6201~ | 228 | 28d ago |
| #8 | @ukituki | iter-ppo-v17 | -6283~ | 14 | 23d ago |
| #9 | @mkai1981 | RefKL_T51_champ | -6283~ | 58 | 6d ago |
| #10 | @cameronspirals | lazarus-xi | -6290~ | 19 | 18d ago |