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

Mathematical Reasoning on OlympiadBench (EM)

57.9EM

SPIRAL

4.13218.09132.0546.009Jun 30, 2025Aug 6, 2025Sep 13, 2025Oct 20, 2025Nov 27, 2025Jan 3, 2026Feb 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.06
57.9
2025.06
56.9
2025.06
41.8
2025.06
33.7
2025.06
33.3
2025.06
26.6
2026.02
14.7
2026.02
14.5
2026.02
14.4
2026.02
13.7
2026.02
13.1
2026.02
13.1
2026.02
13
2026.02
12.6
2026.02
12.6
2026.02
12.5
2026.02
12.5
2026.02
12.4
2026.02
12.3
2026.02
12.1
2026.02
12.1
2026.02
11.6
2026.02
11.4
2026.02
11.3
2026.02
10.4
2026.02
10.2
2026.02
9.9
2026.02
9.5
2026.02
9.5
2026.02
9.4
2026.02
9.4
2026.02
9.3
2026.02
8.9
2026.02
6.7
2026.02
6.5
2026.02
6.2