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

Mathematical Reasoning on OlympiadBench (Accuracy, Tokens)

82.44Accuracy

KnowRL-Nemotron-1.5B

33.726446.373259.0271.6668Jun 4, 2025Aug 1, 2025Sep 29, 2025Nov 26, 2025Jan 24, 2026Mar 23, 2026May 21, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.04
82.44-
2026.04
82.34-
2026.04
80.23-
2026.04
78.68-
2026.04
78.53-
2026.04
78.45-
2026.04
78.41-
2026.04
76.59-
2026.04
74.09-
2026.04
73.89-
2026.04
72.28-
2026.04
71.7-
2025.10
67.3-
2025.10
64-
2025.10
63.6-
2025.10
63.6-
2025.08
56.828,789
2026.03
56.34,024
2026.03
56.14,499
2025.08
56.084,222
2026.05
55.855,015
55.74,010
2025.08
55.3410,339
54.73,498
54.65,974
2025.08
54.67,200
2025.08
54.32,510
2025.08
53.863,712
2025.08
53.566,970
2026.05
53.483,005
2026.05
53.234,255
2026.03
52.54,085
2026.05
51.758,370
2026.03
51.44,571
2026.05
51.162,813
2026.03
50.26,057
2025.10
50.1-
2026.05
49.1-
2025.10
48.6-
2025.10
47.1-
2025.10
45.6-
2026.05
45.4-
2025.08
44.814,921
2026.05
44.692,271
2025.08
44.6611,715
2025.10
44.4-
2025.10
44.1-
2025.10
44.1-
2025.08
43.627,652
2025.10
43.3-
2025.08
43.0311,014
2025.08
43.033,452
2025.08
42.883,657
2025.06
42.5-
2025.10
42.5-
2025.10
42.2-
2025.06
42-
2025.06
42-
2025.06
41.9-
2025.06
41.7-
2025.06
41.7-
2025.06
41.5-
2025.06
41.5-
2025.06
41.3-
2025.06
41.2-
2026.05
41.2-
2025.06
41.1-
2026.05
41.1-
2025.10
41-
2025.10
40.9-
2026.05
40.9-
2025.06
40.8-
2025.10
40.8-
2025.10
40.6-
2025.10
40.6-
2025.10
40.4-
2026.05
40.4-
2026.05
40.3-
2025.06
40.1-
2026.04
39.9-
2025.06
39.7-
2025.06
39.6-
2026.05
39.2-
2025.10
38.5-
2026.05
38.4-
2026.05
38.3-
2025.06
38.1-
2026.05
37.78-
2025.08
37.5-
2026.05
37.5-
2026.05
36.5-
2026.05
36.39-
2026.05
36.12-
2025.08
36.02-
2026.05
35.8-
2026.05
35.8-
2025.06
35.6-
2026.05
35.6-
2026.05
35.6-
2026.05
35.6-
Showing 100 of 213 rows