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

Reasoning on ProcessBench

69.85Accuracy

Qwen3-8B

0.575618.560336.54554.5297Dec 29, 2025Jan 3, 2026Jan 9, 2026Jan 15, 2026Jan 20, 2026Jan 26, 2026Feb 1, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
69.85
2026.02
67.8
2026.02
67.42
2026.02
67.17
2026.02
31.14
2025.12
29.49
2025.12
28.5
2025.12
27.73
2025.12
26.25
2025.12
26.12
2025.12
25.39
2025.12
24.91
2026.02
23.63
2025.12
13.82
2025.12
10.85
2025.12
10.31
2025.12
9.68
2025.12
7.84
2025.12
4.46
2025.12
3.24