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

Mathematical Reasoning on MATH500 (Speedup and Tau metrics)

6.76Speedup

DFLARE

1.042.5254.015.495Jun 1, 2026Jun 5, 2026Jun 10, 2026Jun 15, 2026Jun 19, 2026Jun 24, 2026Jun 29, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.06
6.768.97
2026.06
6.728.95
2026.06
6.297.88
2026.06
6.27.8
2026.06
5.337.34
2026.06
5.257.18
2026.06
5.226.75
2026.06
4.996.39
2026.06
4.25.19
2026.06
3.964.86
2026.06
3.083.91
2026.06
2.993.76
2026.06
2.573.7
2026.06
2.433.57
2026.06
2.423.55
2026.06
2.23.4
2026.06
1.59-
2026.06
1.55-
2026.06
1.53-
2026.06
1.45-
2026.06
1.45-
2026.06
1.42-
2026.06
1.39-
2026.06
1.35-
2026.06
1.34-
2026.06
1.3-
2026.06
1.28-
2026.06
1.26-