GLM-4.6
Change Analysis · 2026 Week31
GLM-4.6 2026 Week31 Code Execution (v5) dimension rose 14.1 pts
Score Comparison
41.5
46.9
+5.4
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 30.3 | 44.4 | +14.1 |
| Knowledge Synthesis (v5) | 43.9 | 44.5 | +0.6 |
| Grounding (v5) | 66.7 | 62.8 | -3.9 |
| Value | 28 | 36.6 | +8.6 |
| Stability | 32.6 | 36.4 | +3.8 |
| Availability | 55.1 | 60.8 | +5.7 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers