Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Human Preference Alignment on Multi-Challenge
Loading...
49.4
Avg@3
Qwen3-30A3-2507
35.256
38.928
42.6
46.272
Dec 6, 2025
Avg@3
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@3
Qwen3-30A3-2507
Release Identifier=2507
2025.12
49.4
Qwen3-4B-2507
Release Identifier=2507
2025.12
41.8
Nanbeige4-3B-Thinking
Release Identifier=2511
2025.12
41.2
Qwen3-32B-2504
Release Identifier=2504
2025.12
39.2
Qwen3-14B-2504
Release Identifier=2504
2025.12
36.4
Qwen3-8B-2504
Release Identifier=2504
2025.12
35.8
Feedback
Search any
task
Search any
task