Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Answering on ARC Challenge (Mean per-step regret)

0.095Mean Per-Step Regret

No-Rewrite (NoRw)

0.09160.114550.13750.16045Feb 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
0.095
2026.02
0.097
2026.02
0.098
2026.02
0.102
2026.02
0.106
2026.02
0.107
2026.02
0.109
2026.02
0.111
2026.02
0.118
2026.02
0.121
2026.02
0.121
2026.02
0.123
2026.02
0.124
2026.02
0.125
2026.02
0.18