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

Mathematical Reasoning on GSM-sym

90.22Exact Match

R1-Oracle

2.610425.355248.170.8448Sep 5, 2025Oct 6, 2025Nov 7, 2025Dec 8, 2025Jan 9, 2026Feb 9, 2026Mar 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
90.2279.120-
2025.09
87.64--323
2025.09
86.76--350
2026.03
86.4477.02-2.1-
2025.09
86.3--414
2025.09
85.42--485
2025.09
85.24--297
2026.03
84.6775.67-3.45-
2025.09
83.52--345
2025.09
79.04--654
2025.09
78.68--644
2026.03
77.7868.1-2.37-
2026.03
75.3370.470-
2025.09
75.02--464
2025.09
73.76--337
2025.09
73.52--344
2025.09
73.36--623
2025.09
72.72--289
2025.09
68.02--369
2025.09
67.66--413
2025.09
67.66--346
2025.09
66.22--435
2025.09
65.78--363
2025.09
64.88--322
2025.09
64.74--320
2025.09
63.54--240
2026.03
62.8962.72-7.75-
2025.09
62.88--460
2025.09
62.24--279
2025.09
57.4--373
2025.09
56.86--398
2025.09
46.76--365
2025.09
34.7--1,552
2025.09
34.52--772
2025.09
32.36--1,063
2025.09
32.06--1,157
2025.09
31--936
2025.09
30.28--1,187
2025.09
27.72--209
2025.09
27.66--174
2025.09
26.52--179
2025.09
25.44--164
2025.09
19.58--427
2025.09
5.98--1,873