Dimension Drop
Severity 10/10
2026-W14
GPT-4o Code Execution (v5)下跌 23.7 分
Score Comparison
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Overall (v5) | 81.1 | 49.3 | -31.8 |
| Code Execution (v5) | 78.0 | 62.8 | -15.2 |
| Knowledge Synthesis (v5) | 79.0 | 47.2 | -31.8 |
| Grounding (v5) | 80.1 | 49.1 | -31 |
| Value | 79.0 | 24.9 | -54.1 |
| Stability | 80.0 | 27.8 | -52.2 |
| Availability | 100.0 | 79.0 | -21 |
Affected Dimensions
Code Execution (v5)
Run #52 · Formula v7 · Judge v6 · Benchmark v6 · 2026-03-30 04:16 SGT
View GPT-4o Full Profile