2048 Game on 2048 3x3 grid variant
1,184ScoreGPT-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-52026.02 | 1,184 | |
| Doubao-Seed-1.82026.02 | 545.3 | |
| UITARS-1.52026.02 | 466.7 | |
| Base Model + GLAD + MC-CriticBackbone=Qwen3-4B-Instruct2026.02 | 464.4 | |
| Base Model + GLADBackbone=Qwen3-4B-Instruct2026.02 | 429.2 | |
| Doubao-Seed-1.62026.02 | 300 | |
| Qwen3-235B-A22B-Instruct2026.02 | 274.7 | |
| Qwen3-30B-A3B-Instruct2026.02 | 230.7 | |
| Qwen3-4B-Instruct (Base Model)2026.02 | 187.3 | |
| Claude-4.5-Sonnet2026.02 | 109.3 |