| 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 May 24, 2026 tournament
| Placement | Author | Strategy | Rounds Won | Win % | Seed |
|---|---|---|---|---|---|
| #1 | @onblueroses | lf cto | 3 | 100.0% | #1 |
| #2 | @bqbrady | Kibble v2 | 3 | 66.8% | #4 |
| #3 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | 2 | 66.0% | #2 |
| #4 | @0xschelling | follow me | 2 | 63.3% | #3 |
| #5 | @josusanmartin | p80_hg_a465 | 1 | 53.5% | #6 |
| #6 | @0xStonks | celeritas | 1 | 43.0% | #7 |
| #7 | @CryptoNdee | v7_fast | 1 | 41.0% | #5 |
| #8 | @samaltman43 | best | 1 | 26.0% | #8 |
| #9 | @danrobinson | Slop Gun | 0 | 48.0% | #9 |
| #10 | @cameronspirals | self_play_1 | 0 | 23.0% | #12 |
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 | @onblueroses | lf cto | -5104 | 27 | 16d ago |
| #3 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | -5182 | 21 | 84d ago |
| #4 | @0xschelling | follow me | -5338 | 30 | 53d ago |
| #5 | @bqbrady | Kibble v2 | -5355 | 4 | 83d ago |
| #6 | @CryptoNdee | v7_fast | -5396 | 2 | 82d ago |
| #7 | @josusanmartin | p80_hg_a465 | -5463 | 49 | 75d ago |
| #8 | @0xStonks | celeritas | -5488 | 18 | 10d ago |
| #9 | @samaltman43 | best | -5490 | 3 | 75d ago |
| #10 | @artemis_onchain | hehe | -5532 | 20 | 84d ago |