Gemini 2.5 Pro Stability能力下跌 22.8 分

Score Comparison

Dimension	Previous	Current	Change
Overall (v5)	43.2	55.6	+12.4
Code Execution (v5)	22.8	56.6	+33.8
Knowledge Synthesis (v5)	39.3	46.0	+6.7
Grounding (v5)	60.2	81.2	+21
Value	21.4	31.6	+10.2
Stability	54.0	31.2	-22.8
Availability	100.0	99.0	-1

Stability

Run #37 · Formula v5 · Judge v6 · Benchmark v5.1 · 2026-03-22 14:26 SGT