DeepSeek R1 has emerged as the leading open-source model for mathematical reasoning, outperforming many closed-source alternatives on MATH and GSM8K benchmarks.
85%
Overall ConfidenceBased on 5 weighted dimensions
Confidence Breakdown
Authority
30%95Tier 1
Data Quality
25%100Level 5
Recency
20%6031-90 days
Corroboration
15%1003 sources
Specificity
10%100Level 4
Data Points(3)
Achieved 88% on MATH benchmark, exceeding GPT-4 baseline
Dec 17, 2025
Available at $0.55/$2.19 input/output pricing
Dec 18, 2025
Open weights enable fine-tuning for specialized math applications
Dec 16, 2025