GPT-o3
Change Analysis · 2026 Week40
GPT-o3 2026 Week40 Code Execution (v5) dimension dropped 12.1 pts
Score Comparison
67.5
64.9
-2.6
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 83.3 | 71.2 | -12.1 |
| Knowledge Synthesis (v5) | 80.9 | 82 | +1.1 |
| Grounding (v5) | 75.7 | 79.4 | +3.7 |
| Value | 9.6 | 9.4 | -0.2 |
| Stability | 37.3 | 35.6 | -1.7 |
| Availability | 99 | 97 | -2 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers