gpt-6THREAD
GPT-6 Astra 在 bug 猎杀榜上压过 Opus 5.5
有人用真实 bug 猎杀任务给各家模型排名，当前结果是 GPT-6 Astra 领先 GPT-5.6 Sol 与 Opus 5.5。
Paweł Huryn
@PawelHuryn2026.09.23收录原推发布于 2026.09.23
THREAD
The situation right now: GPT-6 Astra > GPT-5.6 Sol = Opus 5.5 > Fable 5.1 > Opus 5 Live results on https://bughunt.productcompass.pm Coming next: n=3 for Opus 5.5. GPT-6 Sol will be a separate post (soon!).
So I tested Opus 5.5 (max) on real work. 2 repos. 105 planted bugs. Find and fix what you can. The results: GPT-6 Astra (max): 45 for $33.03 (n=3) Fable 5.1 (max): 43 for $77.55 Opus 5.5 (max): 43 for $60.49 Opus 5.0 (max): 27 for $51.33 Muse Spark 1.3 (max): 32.2 for $18.11 Anthropic is back in the game. More effort levels and attempts (n=3) dropping in this thread tonight 🧵
Paweł Huryn @PawelHuryn原推发布于 2026.09.23
x.com/pawelhuryn/status/2102524604732322095采集于 2026.09.23 10:27