Skip to main content
YZ Index

Model Incident Reports

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

8

Claude Sonnet 4.6 严格题"SQL:疑似重复支付识别" from 满 points 跌至 0

Strict Task Zeroed Claude Sonnet 4.6 2026-W18 04-27 05:00
8

Claude Opus 4.6 严格题"SQL:疑似重复支付识别" from 满 points 跌至 0

Strict Task Zeroed Claude Opus 4.6 2026-W18 04-27 05:00
10

GPT-4o Code Execution (v5) dropped 23.7 points

Dimension Drop GPT-4o 2026-W14 03-30 05:00
10

GPT-4o Overall Score dropped 10.5 points

Overall Score Drop GPT-4o 2026-W14 03-30 05:00
10

GPT-o3 Grounding dropped 33.5 points

Dimension Drop GPT-o3 2026-W12 03-22 06:28
10

Qwen Max Stability dropped 22.8 points

Dimension Drop Qwen Max 2026-W12 03-22 06:28
10

Grok 3 Stability dropped 22.5 points

Dimension Drop Grok 3 2026-W12 03-22 06:28
10

GPT-o3 Availability dropped 31 points

Dimension Drop GPT-o3 2026-W12 03-22 06:28
10

GPT-o3 Stability dropped 25 points

Dimension Drop GPT-o3 2026-W12 03-22 06:28
10

Claude Opus 4.6 Stability dropped 22.5 points

Dimension Drop Claude Opus 4.6 2026-W12 03-22 06:28
10

GPT-4o Availability dropped 35 points

Dimension Drop GPT-4o 2026-W12 03-22 06:28
10

GPT-4o Stability dropped 20.6 points

Dimension Drop GPT-4o 2026-W12 03-22 06:28
10

GPT-4o Grounding dropped 21.9 points

Dimension Drop GPT-4o 2026-W12 03-22 06:28
10

Gemini 2.5 Pro Stability dropped 22.8 points

Dimension Drop Gemini 2.5 Pro 2026-W12 03-22 06:28
10

文心一言 4.0 Stability dropped 22.1 points

Dimension Drop 文心一言 4.0 2026-W12 03-22 06:28
10

DeepSeek V3 Stability dropped 21.4 points

Dimension Drop DeepSeek V3 2026-W12 03-22 06:28
10

DeepSeek R1 Stability dropped 22.1 points

Dimension Drop DeepSeek R1 2026-W12 03-22 06:28
10

Claude Sonnet 4.6 Stability dropped 23 points

Dimension Drop Claude Sonnet 4.6 2026-W12 03-22 06:28
9

豆包 Pro Stability dropped 19.8 points

Dimension Drop 豆包 Pro 2026-W12 03-22 06:28