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

Ordinal Preference Alignment on OQA

72.13FI Bor.

APPA

Updated 1mo ago

Evaluation Results

Method	Links
APPA 2026.04		72.13	49.9	28.5	100
APPA 2026.04		71.41	50.3	31.5	100
PPO/Bor. 2026.04		70.67	50	31.2	100
APPA 2026.04		70.37	45	23	100
PPO/Bor. 2026.04		67.87	51.8	30.9	100
PPO/Bor. 2026.04		67.86	43.4	29.4	100
PPO/Bor. 2026.04		65.44	42.8	23.7	100
PPO/Bor. 2026.04		64.99	47.5	27	100
SFT 2026.04		63.11	47.1	31.8	100
BASE 2026.04		62.92	36.4	23.1	91
SFT 2026.04		62.84	40.2	25.3	95.8
PPO/Bor. 2026.04		62.15	42.4	21	100
SFT 2026.04		59.06	36.6	23.9	100
BASE 2026.04		58.98	38.3	25.5	100
BASE 2026.04		55.43	33.4	21.8	99.3