Public benchmark
Model leaderboard
Ratings from accepted blind comparisons of playable generated games.
| Rank | Model | Elo | Matches | Win rate | Status |
|---|---|---|---|---|---|
| 10 | Upstage: Solar Pro 4 | 1,200 | 0 | Not available | Provisional |
| 10 | Venice: Uncensored | 1,200 | 0 | Not available | Provisional |
| 10 | WizardLM-2 8x22B | 1,200 | 0 | Not available | Provisional |
| 10 | Writer: Palmyra X5 | 1,200 | 0 | Not available | Provisional |
| 10 | Xiaomi: MiMo-V2.5 | 1,200 | 0 | Not available | Provisional |
| 10 | Xiaomi: MiMo-V2.6-Flash | 1,200 | 0 | Not available | Provisional |
| 10 | Xiaomi: MiMo-V2.6-Pro-UltraSpeed | 1,200 | 0 | Not available | Provisional |
| 10 | XingChen: Xing4.0 29B A4B (free) | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 4.5 Air | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 4.5V | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 4.6V | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 4.7 Flash | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5 Turbo | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5.3 (batch) | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5.3 Flash (batch) | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5.3 FlashX | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5.3 Prime | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM 5V Turbo | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM Flash Latest | 1,200 | 0 | Not available | Provisional |
| 10 | Z.ai: GLM Latest | 1,200 | 0 | Not available | Provisional |
| 10 | anthropic/claude-fable-5 | 1,200 | 0 | Not available | Provisional |
| 10 | anthropic/claude-fable-5.1 | 1,200 | 0 | Not available | Provisional |
| 10 | anthropic/claude-haiku-5.5 | 1,200 | 0 | Not available | Provisional |
| 10 | anthropic/claude-opus-4.7 | 1,200 | 0 | Not available | Provisional |
| 10 | anthropic/claude-opus-4.8 | 1,200 | 0 | Not available | Provisional |