Algorithmic Reasoning on Word Sorting
1Acc@t1SELF-THOUGHT
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SELF-THOUGHTModel=GPT-4O-MINI2026.01 | 1 | 45 | 0 | |
| SELF-THOUGHTModel=GPT-4O2026.01 | 1 | 13.75 | 0 | |
| SELF-THOUGHTModel=DEEPSEEK-R12026.01 | 1 | 2.5 | 0 | |
| REFLEXIONModel=O3-MINI2026.01 | 0.975 | 7.5 | 0 | |
| SELF-THOUGHTModel=O3-MINI2026.01 | 0.975 | 8.75 | 1.25 | |
| INITIAL (t = 0)Model=DEEPSEEK-R12026.01 | 0.975 | — | — | |
| REFLEXModel=DEEPSEEK-R12026.01 | 0.9375 | 2.5 | 6.25 | |
| SELF-TICKModel=DEEPSEEK-R12026.01 | 0.9125 | 0 | 6.25 | |
| INITIAL (t = 0)Model=O3-MINI2026.01 | 0.9 | — | — | |
| REFLEXModel=O3-MINI2026.01 | 0.9 | 8.75 | 8.75 | |
| REFLEXIONModel=DEEPSEEK-R12026.01 | 0.9 | 0 | 7.5 | |
| SELF-REFINEModel=DEEPSEEK-R12026.01 | 0.8875 | 1.25 | 10 | |
| SELF-REFINEModel=O3-MINI2026.01 | 0.875 | 8.75 | 11.25 | |
| SELF-TICKModel=O3-MINI2026.01 | 0.875 | 7.5 | 10 | |
| INITIAL (t = 0)Model=GPT-4O2026.01 | 0.8625 | — | — | |
| REFLEXIONModel=GPT-4O2026.01 | 0.825 | 6.25 | 10 | |
| REFLEXModel=GPT-4O2026.01 | 0.8125 | 3.75 | 8.75 | |
| SELF-REFINEModel=GPT-4O2026.01 | 0.7875 | 7.5 | 15 | |
| SELF-TICKModel=GPT-4O2026.01 | 0.7 | 3.75 | 20 | |
| REFLEXModel=GPT-4O-MINI2026.01 | 0.6 | 7.5 | 2.5 | |
| REFLEXIONModel=GPT-4O-MINI2026.01 | 0.6 | 11.25 | 6.25 | |
| SELF-REFINEModel=GPT-4O-MINI2026.01 | 0.5875 | 7.5 | 3.75 | |
| INITIAL (t = 0)Model=GPT-4O-MINI2026.01 | 0.55 | — | — | |
| SELF-TICKModel=GPT-4O-MINI2026.01 | 0.4 | 7.5 | 22.5 |