Qwen3-Coder-30B-A3B-Instruct

Quality rebounds 12.9 points to 85.1 as factual performance recovers

Qwen3-Coder-30B-A3B-Instruct has demonstrated a significant recovery in this benchmark window, climbing from 72.2 to 85.1 in overall quality score. The most dramatic improvement came from factual performance, which surged from a critically low 14 to a respectable 71, addressing the collapse that defined the previous period. Coding performance remains rock-solid at 92, maintaining consistency across both windows, while multilingual capabilities continue to excel at 92. The reasoning category, which scored a perfect 100 previously, was not tested in the current window, and creative writing was also absent from this evaluation period. Latency increased moderately from 2544ms to 2898ms at the median, representing approximately a 14% slowdown. This trade-off between speed and quality suggests potential model adjustments or infrastructure changes. With five test runs in both windows, the sample size provides reasonable confidence in these results. Users can expect strong coding and multilingual capabilities with much-improved factual accuracy compared to the previous window, though the latency increase may impact time-sensitive applications. The model appears to have stabilized after its previous quality drop.