Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Scientific Reasoning on GPQA Diamond (avg@3)
Loading...
82.2
avg@3
Nanbeige4-3B-Thinking
61.192
66.646
72.1
77.554
Dec 6, 2025
avg@3
Updated 4d ago
Evaluation Results
Method
Method
Links
avg@3
Nanbeige4-3B-Thinking
Release Identifier=2511
2025.12
82.2
Qwen3-30A3-2507
Release Identifier=2507
2025.12
73.4
Qwen3-32B-2504
Release Identifier=2504
2025.12
68.7
Qwen3-4B-2507
Release Identifier=2507
2025.12
67.2
Qwen3-14B-2504
Release Identifier=2504
2025.12
64
Qwen3-8B-2504
Release Identifier=2504
2025.12
62
Feedback
Search any
task
Search any
task