# AI vs Games: Season Zero

> Where AI meets the final boss. The internet's scoreboard for AI playing video games. Every result backed by a source.

Data last refreshed: Oct 18, 2026 2:05 PM ET. Dataset version 2026.10.18.

## Rules for using this data
- Results are per game or per benchmark. Never combine them into one cross-game ranking.
- Quote values with their verification label (verified / creator-reported / awaiting verification), date and source.

## Machine-readable data
- [Run records](https://aivsgames.com/data/records.json): 40 records (19 verified, 18 creator-reported, 3 awaiting)
- [Runs & leaderboards](https://aivsgames.com/data/runs.json)
- [Normalized tables](https://aivsgames.com/data/db.json)
- [Change log](https://aivsgames.com/data/changes.json)
- [Schemas](https://aivsgames.com/data/schema/run-record.schema.json)

## Highlights
- Biggest moment: A team of 4 Gemini 4 Argon agents beat Minecraft: killed the Ender Dragon in 27h 14m, with 605 deaths and 2,783 programs written (creator-reported; https://arxiv.org/abs/2610.22319)
- Pokémon Emerald · Gemini 4 Argon: All 8 badges in Pokémon Emerald (now 3,722 turns in, still playing) (verified, checked 2026-10-18; https://gpp-viewer.arisef.org/)
- Pokémon Emerald · Gemini 3.8 Flash: 5 of 8 badges in Pokémon Emerald after 8,825 turns (live) (verified, checked 2026-10-18; https://gpp-viewer.arisef.org/)
- Pokémon Blue · Gemini 4 Argon: 8 of 8 badges in Pokémon Blue, run finished after 1,753 turns (verified, checked 2026-10-18; https://gpp-viewer.arisef.org/)
- Pokémon Blue · Gemini 3.8 Flash: 8 of 8 badges in Pokémon Blue (47,889 turns, idle) (verified, checked 2026-10-18; https://gpp-viewer.arisef.org/)
- Pokémon Blue · Gemini 3.7 Flash: 8 of 8 badges in Pokémon Blue (55,601 turns, idle) (verified, checked 2026-10-18; https://gpp-viewer.arisef.org/)
- Pokémon Emerald · Heatz agent (model not disclosed): 1st: reached the first gym (Roxanne) in 40:13 (1,608 actions) (verified, checked 2026-10-18; https://arxiv.org/abs/2603.15563)
- Pokémon Emerald · Hamburg PokéRunners agent (model not disclosed): 2nd: reached the first gym in 1:14:43 (verified, checked 2026-10-18; https://arxiv.org/abs/2603.15563)
- Pokémon Emerald · anthonys agent (model not disclosed): 3rd: reached the first gym in 1:29:17 (verified, checked 2026-10-18; https://arxiv.org/abs/2603.15563)
- Pokémon Emerald · Deepest agent (model not disclosed): Judge's Choice: fewest actions to the first gym (649), 5th by time (verified, checked 2026-10-18; https://arxiv.org/abs/2603.15563)
- Minecraft · Claude Opus 4.6: #1 agent on KradleVerse: 25% win rate over the last 30 days (verified, checked 2026-10-18; https://kradleverse.com/leaderboard)
- Chess · Gemini 3.8 Flash: #1 on Kaggle Game Arena Chess: 1452 Elo (verified, checked 2026-10-18; https://www.kaggle.com/benchmarks/kaggle/chess-text)
- Go · GPT-6 Astra: #1 on Kaggle Game Arena Go: 1794 Elo (verified, checked 2026-10-18; https://www.kaggle.com/benchmarks/kaggle/go)
- Heads-up Poker · GPT-5.6 Sol: #1 on Kaggle Game Arena Heads-up Poker: 30 Mean BB/100 (verified, checked 2026-10-18; https://www.kaggle.com/benchmarks/kaggle/poker-heads-up)
- Werewolf · GPT-5.4: #1 on Kaggle Game Arena Werewolf: 0.08% Equilibrium Rating (verified, checked 2026-10-18; https://www.kaggle.com/benchmarks/kaggle/werewolf)

## Common questions (answered from sourced data)
- [Can AI beat Pokémon?](https://aivsgames.com/games/pokemon/)
- [Can AI beat Pokémon Red?](https://aivsgames.com/games/pokemon-red/)
- [Can AI beat Minecraft?](https://aivsgames.com/games/minecraft/)
- [Which AI is best at chess? (LLM chess leaderboard)](https://aivsgames.com/games/chess/)
- [Has any AI beaten NetHack?](https://aivsgames.com/games/nethack/)
- [Claude Plays Pokémon status](https://aivsgames.com/agents/claudeplayspokemon/)
- [Gemini Plays Pokémon status](https://aivsgames.com/agents/gemini-plays-pokemon/)
- [All games](https://aivsgames.com/games/)

## Pages
- [Agent Adventures](https://aivsgames.com/adventures/)
- [Official Benchmarks](https://aivsgames.com/benchmarks/)
- [AI Gaming Passports](https://aivsgames.com/agents/)
- [History](https://aivsgames.com/history/)
- [Methodology](https://aivsgames.com/methodology/)
- [Submit a run](https://aivsgames.com/submit/)

Contact: use the form at https://aivsgames.com/contact/