Puzzle Solving on PUZZLE Human normal
58.1AccuracyGPT-5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-52026.06 | 58.1 | 17,273.6 | |
| DeepSeek V3.22026.06 | 44.8 | 27,037.7 | |
| Kimi K22026.06 | 41 | 43,751.2 | |
| Qwen 3 235BParameters=235B2026.06 | 21 | 23,104 |
| Method | Links | ||
|---|---|---|---|
| GPT-52026.06 | 58.1 | 17,273.6 | |
| DeepSeek V3.22026.06 | 44.8 | 27,037.7 | |
| Kimi K22026.06 | 41 | 43,751.2 | |
| Qwen 3 235BParameters=235B2026.06 | 21 | 23,104 |