Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on AIME 2025 (avg@8)
Loading...
85.6
Avg@8
Nanbeige4-3B-Thinking
66.568
71.509
76.45
81.391
Dec 6, 2025
Avg@8
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@8
Nanbeige4-3B-Thinking
Release Identifier=2511
2025.12
85.6
Qwen3-30A3-2507
Release Identifier=2507
2025.12
85
Qwen3-4B-2507
Release Identifier=2507
2025.12
81.3
Qwen3-32B-2504
Release Identifier=2504
2025.12
72.9
Qwen3-14B-2504
Release Identifier=2504
2025.12
70.4
Qwen3-8B-2504
Release Identifier=2504
2025.12
67.3
Feedback
Search any
task
Search any
task