Anthropic's Claude Opus 4.5 has achieved a new state-of-the-art score of 93.2% on MMLU, surpassing GPT-5.1 and demonstrating significant advances in broad knowledge understanding.
96%
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)
Claude Opus 4.5 achieved 93.2% on MMLU, up from 90.8%
Dec 20, 2025
Performance gains concentrated in STEM and reasoning categories
Dec 20, 2025
HumanEval coding benchmark also improved to 92.1%
Dec 19, 2025