Public benchmark
Model leaderboard
Ratings from accepted blind comparisons of playable generated games.
| Rank | Model | Elo | Matches | Win rate | Status |
|---|---|---|---|---|---|
| 10 | Google: Gemma 3 4B | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Gemma 4 26B A4B | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Gemma 4 26B A4B (free) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Gemma 4 31B (free) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Lyria 3 Clip Preview | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Lyria 3 Pro Preview | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana (Gemini 2.5 Flash Image) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana 2 (Gemini 3.1 Flash Image) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana 2.1 | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana Pro (Gemini 3 Pro Image Preview) | 1,200 | 0 | Not available | Provisional |
| 10 | Google: Nano Banana Pro (Gemini 3 Pro Image) | 1,200 | 0 | Not available | Provisional |
| 10 | IBM: Granite 4.0 Micro | 1,200 | 0 | Not available | Provisional |
| 10 | IBM: Granite 4.2 8B | 1,200 | 0 | Not available | Provisional |
| 10 | Inception: Mercury 2 | 1,200 | 0 | Not available | Provisional |
| 10 | Inception: Mercury 2.5 | 1,200 | 0 | Not available | Provisional |
| 10 | Inference.net: Schematron V2 Small | 1,200 | 0 | Not available | Provisional |
| 10 | Inference.net: Schematron V2 Turbo | 1,200 | 0 | Not available | Provisional |
| 10 | Kwaipilot: KAT-Coder-Pro V2.5 | 1,200 | 0 | Not available | Provisional |
| 10 | LiquidAI: LFM2.5-2.6B (free) | 1,200 | 0 | Not available | Provisional |
| 10 | LiquidAI: LFM2.5-24B-A2B | 1,200 | 0 | Not available | Provisional |
| 10 | Magnum v4 72B | 1,200 | 0 | Not available | Provisional |
| 10 | Mancer: Weaver (alpha) | 1,200 | 0 | Not available | Provisional |
| 10 | Meituan: LongCat 2.0 | 1,200 | 0 | Not available | Provisional |