Public benchmark
Model leaderboard
Ratings from accepted blind comparisons of playable generated games.
| Rank | Model | Elo | Matches | Win rate | Status |
|---|---|---|---|---|---|
| 10 | meta/muse-spark-1.2-contributor | 1,200 | 0 | Not available | Provisional |
| 10 | minimax/minimax-m1:extended | 1,200 | 0 | Not available | Provisional |
| 10 | minimax/minimax-m3 | 1,200 | 0 | Not available | Provisional |
| 10 | mistralai/codestral-embed-2505 | 1,200 | 0 | Not available | Provisional |
| 10 | mistralai/devstral-medium-2507 | 1,200 | 0 | Not available | Provisional |
| 10 | moonshotai/kimi-k2-thinking | 1,200 | 0 | Not available | Provisional |
| 10 | moonshotai/kimi-k2.6 | 1,200 | 0 | Not available | Provisional |
| 10 | moonshotai/kimi-k3 | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5-codex | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5-mini | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5-pro | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5.2-codex | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5.2-pro | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5.4 | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5.5 | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-5.6-luna | 1,200 | 0 | Not available | Provisional |
| 10 | openai/gpt-oss-120b | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/fusion | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/healer-alpha | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/horizon-alpha | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/hunter-alpha | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/pony-alpha | 1,200 | 0 | Not available | Provisional |
| 10 | openrouter/sherlock-dash-alpha | 1,200 | 0 | Not available | Provisional |
| 10 | qwen/qwen3-coder-next | 1,200 | 0 | Not available | Provisional |
| 10 | qwen/qwen3.6-max-preview | 1,200 | 0 | Not available | Provisional |