GPT-o3
Change Analysis · 2026 Week27
GPT-o3 2026 Week27 Code Execution (v5) dimension dropped 19.1 pts
Score Comparison
75.4
69.7
-5.7
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 87.2 | 68.1 | -19.1 |
| Knowledge Synthesis (v5) | 89.4 | 89 | -0.4 |
| Grounding (v5) | 93.6 | 94.9 | +1.3 |
| Value | 10.8 | 10.2 | -0.6 |
| Stability | 57.8 | 51 | -6.8 |
| Availability | 98 | 95.9 | -2.1 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers