HNHacker News·
Archived topic · source no longer tracked
Qwen 3.8 follows GPT-5.5 Pro reasoning prefills
A recent analysis of reasoning prefills across several open models, including DeepSeek V4 Flash, Inkling, Kimi K3, and Qwen3.8 A95B, shows varying degrees of alignment with GPT-5.5 Pro. Qwen3.8 A95B demonstrated a significant improvement of +18.18 pp when using reasoning prefills, increasing its overlap from 16.79% to 34.97%. Kimi K3, while having the highest overall overlap with GPT-5.5 Pro (31.11% unprefilled, 35.65% with prefill), saw a smaller gain of +4.54 points from the prefill.
Time & source
Times shown in UTC
Display time zone: UTC
Local time zone unavailable; showing UTC.
IngestedOffset at this time: UTC+0Sep 9, 2026, 19:00 UTC
- Ingested
- Sep 9, 2026, 19:00
- Source type
- Dev community
- Basis
- Running about 2.1× the median of this source's recent listed items
- Triggering item
- Qwen 3.8 follows GPT-5.5 Pro reasoning prefills
- Metric comparison
- 148 vs median 69 (20 baseline samples)
- Detected
- 09/09, 23:00
Full text isn't available here.
Read at source →