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

Text Reasoning on In-domain (test)

66.6Accuracy

RLVR

10.9625.40539.8554.295Jul 2, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
66.60.5140.285
2026.07
65.10.7510.109
2026.07
64.90.70.119
2026.07
64.40.7480.076
2026.07
550.8070.075
2026.07
53.90.7620.088
2026.07
49.10.7340.142
2026.07
49.10.7340.142
2026.07
480.720.098
2026.07
47.30.6970.136
2026.07
47.30.6970.136
2026.07
45.90.5870.463
2026.07
45.90.5870.463
2026.07
45.30.5310.448
2026.07
43.30.7990.072
2026.07
43.30.7990.072
2026.07
40.80.7870.091
2026.07
40.80.7870.091
2026.07
37.60.5720.168
2026.07
37.60.5720.168
2026.07
37.20.5630.134
2026.07
37.20.5630.134
2026.07
13.10.6760.06
2026.07
13.10.6760.06