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

Mathematical Reasoning on MATH500 (avg@1)

93.6Average Score (avg@1)

NPR

Updated 4d ago

Evaluation Results

Method	Links
NPR 2025.12		93.6
Qwen3-4B-Instruct-2507 2025.12		93.4
SR 2025.12		92.8
SR-BETA 2025.12		92
Multiverse-32B 2025.12		91.8
NPR (Variant) 2025.12		91.8
NPR-BETA 2025.12		91.6
NPR-BETA (Variant) 2025.12		86.8
Qwen3-4B (Non-Thinking) 2025.12		84.8
Multiverse-4B 2025.12		81.6
Qwen2.5-32B-Instruct 2025.12		80.4