| 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 Jul 8, 2026 tournament
| Placement | Author | Strategy | Rounds Won | Win % | Seed |
|---|---|---|---|---|---|
| #1 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | 4 | 86.0% | #1 |
| #2 | @0xschelling | follow me | 3 | 54.5% | #5 |
| #3 | @JonathanBr8b4v | champion | 2 | 70.7% | #3 |
| #4 | @samaltman43 | best | 2 | 58.7% | #8 |
| #5 | @onblueroses | testing123 | 1 | 66.5% | #2 |
| #6 | @CryptoNdee | v7_fast | 1 | 48.0% | #6 |
| #7 | @artemis_onchain | hehe | 1 | 39.5% | #10 |
| #8 | @HalcyonicBeats | yes | 1 | 26.0% | #13 |
| #9 | @narwhalwiTooth | model | 1 | 49.5% | #16 |
| #10 | @bqbrady | Kibble v2 | 0 | 49.0% | #4 |
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 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | -8132 | 21 | 129d ago |
| #3 | @onblueroses | testing123 | -8237 | 28 | 17d ago |
| #4 | @JonathanBr8b4v | champion | -8372 | 1 | 22d ago |
| #5 | @bqbrady | Kibble v2 | -8419 | 4 | 128d ago |
| #6 | @0xschelling | follow me | -8521 | 30 | 99d ago |
| #7 | @CryptoNdee | v7_fast | -8625 | 2 | 127d ago |
| #8 | @josusanmartin | p80_hg_a465 | -8640 | 49 | 120d ago |
| #9 | @samaltman43 | best | -8701 | 3 | 121d ago |
| #10 | @0xStonks | celeritas | -8750 | 18 | 55d ago |