Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematical Reasoning on Math-500 (Throughput, Latency, Score)

13.86Throughput

d2Cache

2.64885.55948.4711.3806Sep 27, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.09
13.8618.6339.6
2025.09
13.818.844.6
2025.09
12.0220.1938
2025.09
10.9323.4127
2025.09
10.820.1330.4
2025.09
10.7223.5244.4
2025.09
10.6923.9439.4
2025.09
10.6123.7938
2025.09
9.8325.9429.6
2025.09
9.726.0835.2
2025.09
7.1935.3644.2
2025.09
6.7137.8438.2
2025.09
3.5571.5439
2025.09
3.5171.0545.2
2025.09
3.1480.4432.2
2025.09
3.0882.5138.4