Public benchmark
Model leaderboard
Ratings from accepted blind comparisons of playable generated games.
| Rank | Model | Elo | Matches | Win rate | Status |
|---|---|---|---|---|---|
| 10 | OpenAI: o3 Mini (batch) | 1,200 | 0 | Not available | Provisional |
| 10 | OpenAI: o3 Mini High | 1,200 | 0 | Not available | Provisional |
| 10 | OpenAI: o4 Mini | 1,200 | 0 | Not available | Provisional |
| 10 | OpenAI: o4 Mini (batch) | 1,200 | 0 | Not available | Provisional |
| 10 | Pareto | 1,200 | 0 | Not available | Provisional |
| 10 | Pareto 26.10 Preview | 1,200 | 0 | Not available | Provisional |
| 10 | Pareto 26.9 | 1,200 | 0 | Not available | Provisional |
| 10 | Pareto Latest | 1,200 | 0 | Not available | Provisional |
| 10 | Perceptron: Perceptron Mk1 | 1,200 | 0 | Not available | Provisional |
| 10 | Perceptron: Perceptron Mk1.5 | 1,200 | 0 | Not available | Provisional |
| 10 | Perplexity: Sonar | 1,200 | 0 | Not available | Provisional |
| 10 | Perplexity: Sonar Deep Research | 1,200 | 0 | Not available | Provisional |
| 10 | Perplexity: Sonar Pro | 1,200 | 0 | Not available | Provisional |
| 10 | Perplexity: Sonar Pro Search | 1,200 | 0 | Not available | Provisional |
| 10 | Perplexity: Sonar Reasoning Pro | 1,200 | 0 | Not available | Provisional |
| 10 | Poolside: Laguna S 2.1 | 1,200 | 0 | Not available | Provisional |
| 10 | Poolside: Laguna S 2.1 (free) | 1,200 | 0 | Not available | Provisional |
| 10 | Poolside: Laguna XS 2.1 | 1,200 | 0 | Not available | Provisional |
| 10 | Poolside: Laguna XS 2.1 (free) | 1,200 | 0 | Not available | Provisional |
| 10 | PrismML: Ternary Bonsai 2 27B | 1,200 | 0 | Not available | Provisional |
| 10 | Qwen2.5 72B Instruct | 1,200 | 0 | Not available | Provisional |
| 10 | Qwen2.5 Coder 32B Instruct | 1,200 | 0 | Not available | Provisional |
| 10 | Qwen: Qwen Plus 0728 | 1,200 | 0 | Not available | Provisional |
| 10 | Qwen: Qwen-Plus | 1,200 | 0 | Not available | Provisional |
| 10 | Qwen: Qwen2.5 7B Instruct | 1,200 | 0 | Not available | Provisional |