Dimension Drop
Severity 10/10
2026-W12
DeepSeek R1 Stability下跌 22.1 分
Score Comparison
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Overall (v5) | 49.0 | 65.8 | +16.8 |
| Code Execution (v5) | 20.5 | 67.9 | +47.4 |
| Knowledge Synthesis (v5) | 36.4 | 42.9 | +6.5 |
| Grounding (v5) | 60.2 | 78.3 | +18.1 |
| Value | 69.4 | 88.1 | +18.7 |
| Stability | 53.7 | 31.6 | -22.1 |
| 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 DeepSeek R1 Full Profile