GPT-o3
Change Analysis · 2026 Week15
GPT-o3 2026 Week15 Stability dimension rose 2.2 pts
Score Comparison
55.0
52.9
-2.1
| Dimension | Previous | Current | Change |
|---|---|---|---|
| Code Execution (v5) | 84.7 | 80.3 | -4.4 |
| Knowledge Synthesis (v5) | 47.2 | 47.1 | -0.1 |
| Grounding (v5) | 56.9 | 53 | -3.9 |
| Value | 7.7 | 7.2 | -0.5 |
| Stability | 29 | 31.2 | +2.2 |
| Availability | 93.9 | 89 | -4.9 |
All matched tasks had no score changes, or no tasks could be matched to the previous evaluation.
Back to Movers