GPT-o3
Change Analysis · 2026 Week30
GPT-o3 2026 Week30 Code Execution (v5) dimension rose 5.6 pts
Score Comparison
64.5
66.6
+2.1
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 70.3 | 75.9 | +5.6 |
| Knowledge Synthesis (v5) | 82.5 | 86.8 | +4.3 |
| Grounding (v5) | 77.9 | 74 | -3.9 |
| Value | 9.3 | 9.6 | +0.3 |
| Stability | 34.6 | 35.1 | +0.5 |
| Availability | 98 | 99 | +1 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers