| 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 Mar 27, 2026 tournament
| Placement | Author | Strategy | Rounds Won | Win % | Seed |
|---|---|---|---|---|---|
| #1 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | 3 | 92.0% | #1 |
| #2 | @bqbrady | Kibble v2 | 2 | 65.0% | #3 |
| #3 | @0xschelling | follow me | 1 | 40.5% | #2 |
| #4 | @artemis_onchain | hehe | 1 | 35.5% | #4 |
| #5 | @josusanmartin | p80_hg_a465 | 0 | 45.0% | #5 |
| #6 | @samaltman43 | best | 1 | 35.0% | #7 |
| #7 | @evilboyajay | start | 1 | 28.0% | #9 |
| #8 | @CryptoNdee | v7_fast | 0 | 5.0% | #6 |
| #9 | @HalcyonicBeats | yes | 0 | 44.0% | #10 |
| #10 | @danrobinson | Slop Gun | 0 | 34.0% | #8 |
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 | -856 | 21 | 26d ago |
| #3 | @0xschelling | follow me | -1317 | 26 | 6d ago |
| #4 | @bqbrady | Kibble v2 | -1334 | 4 | 25d ago |
| #5 | @samaltman43 | best | -1399 | 3 | 18d ago |
| #6 | @josusanmartin | p80_hg_a465 | -1409 | 49 | 17d ago |
| #7 | @CryptoNdee | v7_fast | -1421 | 2 | 24d ago |
| #8 | @artemis_onchain | hehe | -1425 | 20 | 27d ago |
| #9 | @danrobinson | Slop Gun | -1432 | 5 | 30d ago |
| #10 | @evilboyajay | start | -1543 | 7 | 19d ago |