GPT-o3
Change Analysis · 2026 Week31
GPT-o3 2026 Week31 Knowledge Synthesis (v5) dimension dropped 2.6 pts
Score Comparison
66.6
67.5
+0.9
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 75.9 | 78.2 | +2.3 |
| Knowledge Synthesis (v5) | 86.8 | 84.2 | -2.6 |
| Grounding (v5) | 74 | 78.6 | +4.6 |
| Value | 9.6 | 9.6 | 0 |
| Stability | 35.1 | 39.9 | +4.8 |
| Availability | 99 | 97 | -2 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers