Dimension Drop
Severity 10/10
2026-W12
Qwen Max Stability下跌 22.8 分
Score Comparison
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Overall (v5) | 42.2 | 56.3 | +14.1 |
| Code Execution (v5) | 20.2 | 58.8 | +38.6 |
| Knowledge Synthesis (v5) | 34.4 | 40.8 | +6.4 |
| Grounding (v5) | 60.2 | 80.6 | +20.4 |
| Value | 27.9 | 42.2 | +14.3 |
| Stability | 53.0 | 30.2 | -22.8 |
| 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 Qwen Max Full Profile