List your company

Algorithmic Reasoning on Word Sorting

1Acc@t1SELF-THOUGHT
0.3760.5380.70.862Jan 31, 2026

Evaluation results

MethodLinks
SELF-THOUGHTModel=GPT-4O-MINI2026.011450
SELF-THOUGHTModel=GPT-4O2026.01113.750
SELF-THOUGHTModel=DEEPSEEK-R12026.0112.50
REFLEXIONModel=O3-MINI2026.010.9757.50
SELF-THOUGHTModel=O3-MINI2026.010.9758.751.25
INITIAL (t = 0)Model=DEEPSEEK-R12026.010.975——
REFLEXModel=DEEPSEEK-R12026.010.93752.56.25
SELF-TICKModel=DEEPSEEK-R12026.010.912506.25
INITIAL (t = 0)Model=O3-MINI2026.010.9——
REFLEXModel=O3-MINI2026.010.98.758.75
REFLEXIONModel=DEEPSEEK-R12026.010.907.5
SELF-REFINEModel=DEEPSEEK-R12026.010.88751.2510
SELF-REFINEModel=O3-MINI2026.010.8758.7511.25
SELF-TICKModel=O3-MINI2026.010.8757.510
INITIAL (t = 0)Model=GPT-4O2026.010.8625——
REFLEXIONModel=GPT-4O2026.010.8256.2510
REFLEXModel=GPT-4O2026.010.81253.758.75
SELF-REFINEModel=GPT-4O2026.010.78757.515
SELF-TICKModel=GPT-4O2026.010.73.7520
REFLEXModel=GPT-4O-MINI2026.010.67.52.5
REFLEXIONModel=GPT-4O-MINI2026.010.611.256.25
SELF-REFINEModel=GPT-4O-MINI2026.010.58757.53.75
INITIAL (t = 0)Model=GPT-4O-MINI2026.010.55——
SELF-TICKModel=GPT-4O-MINI2026.010.47.522.5