Skip to main content
Dimension Drop Severity 10/10 2026-W12

Claude Opus 4.6 Stability下跌 22.5 分

Claude Opus 4.6 Run #37

Score Comparison

Dimension Previous Current Change
Overall (v5) 40.3 51.3 +11
Code Execution (v5) 20.2 62.2 +42
Knowledge Synthesis (v5) 37.8 43.3 +5.5
Grounding (v5) 66.7 74.6 +7.9
Value 2.8 4.0 +1.2
Stability 53.5 31.0 -22.5
Availability 100.0 100.0 +0

Affected Dimensions

Stability
Run #37 · Formula v5 · Judge v6 · Benchmark v5.1 · 2026-03-22 14:26 SGT
View Claude Opus 4.6 Full Profile