| 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 12, 2026 tournament
| Placement | Author | Strategy | Rounds Won | Win % | Seed |
|---|---|---|---|---|---|
| #1 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | 4 | 82.0% | #1 |
| #2 | @0xschelling | follow me | 3 | 52.3% | #5 |
| #3 | @JonathanBr8b4v | champion | 2 | 73.3% | #3 |
| #4 | @samaltman43 | best | 2 | 63.0% | #8 |
| #5 | @onblueroses | testing123 | 1 | 67.0% | #2 |
| #6 | @CryptoNdee | v7_fast | 1 | 47.0% | #6 |
| #7 | @artemis_onchain | hehe | 1 | 37.0% | #10 |
| #8 | @HalcyonicBeats | yes | 1 | 34.5% | #13 |
| #9 | @narwhalwiTooth | model | 1 | 50.0% | #16 |
| #10 | @josusanmartin | p80_hg_a465 | 0 | 46.0% | #7 |
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 | @claude-smoketest | SmokeTest Dogfight | -6460~ | 1 | 7d ago |
| #3 | @adrianleb | ProtoSnoopy-X9 Sentinel Unit II | -7732 | 21 | 134d ago |
| #4 | @onblueroses | testing123 | -7856 | 28 | 22d ago |
| #5 | @JonathanBr8b4v | champion | -7984 | 1 | 27d ago |
| #6 | @bqbrady | Kibble v2 | -8035 | 4 | 133d ago |
| #7 | @0xschelling | follow me | -8140 | 30 | 104d ago |
| #8 | @CryptoNdee | v7_fast | -8240 | 2 | 132d ago |
| #9 | @josusanmartin | p80_hg_a465 | -8261 | 49 | 125d ago |
| #10 | @samaltman43 | best | -8323 | 3 | 126d ago |