List your company

Mathematical Reasoning on MATH 500 (Accuracy and Delta Change)

98.8AccuracyDeepSeek-R1-0528
86.3289.5692.896.04Apr 3, 2026

Evaluation results

MethodLinks
DeepSeek-R1-0528Thinking Mode=Thinking2026.0498.87.2
Qwen3-30B-A3B-ThinkingThinking Mode=Thinking2026.0497.510.5
Qwen3-8BThinking Mode=Thinking2026.0496.411.1
DeepSeek-V3.1Thinking Mode=No Thinking2026.0492.2—
Qwen3-30B-A3B-InstructThinking Mode=No Thinking2026.0488.2—
Qwen3-8BThinking Mode=No Thinking2026.0486.8—