Skip to main content
YZ Index

Model Incident Reports

Auto-detected: overall crash / dimension collapse / strict task zeroed · updated weekly

All 2026-W24 2026-W22 2026-W20 2026-W19 2026-W14 2026-W12
All Types Overall Score Drop Dimension Drop Strict Task Zeroed
10

Gemini 2.5 Pro Overall Score Dropped 19.5 points

Overall Score Drop Gemini 2.5 Pro 2026-W22 05-25 08:30
10

Gemini 2.5 Pro Code Execution (v5) dropped 33.4 points

Dimension Drop Gemini 2.5 Pro 2026-W22 05-25 08:30
10

Gemini 2.5 Pro Grounding (v5) dropped 29 points

Dimension Drop Gemini 2.5 Pro 2026-W22 05-25 08:30
10

Gemini 2.5 Pro Availability dropped 24 points

Dimension Drop Gemini 2.5 Pro 2026-W22 05-25 08:30

Winzheng — Incidents are auto-detected after each weekly evaluation