Puzzle Solving on PUZZLE (Trivial)
83.8AccuracyGPT-5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-52026.06 | 83.8 | 4,153.5 | |
| DeepSeek V3.22026.06 | 77.1 | 7,694.7 | |
| Kimi K22026.06 | 77.1 | 10,601.5 | |
| Qwen 3 235BParameters=235B2026.06 | 69.5 | 10,257.3 |
| Method | Links | ||
|---|---|---|---|
| GPT-52026.06 | 83.8 | 4,153.5 | |
| DeepSeek V3.22026.06 | 77.1 | 7,694.7 | |
| Kimi K22026.06 | 77.1 | 10,601.5 | |
| Qwen 3 235BParameters=235B2026.06 | 69.5 | 10,257.3 |