Bug Hunt Bench Tests Models on 105 Real Bugs, Cost Gap Nears 200x

Pawel Huryn's Bug Hunt Bench evaluates frontier coding models on 105 real bugs from Xiaomi repos with blind judges, finding a nearly 200x cost gap—Xiaomi's MiMo-V2.6-Pro scored 22.7 for just $0.86.

2026-09-22 ~ 2026-09-22 · 3 related posts

• Xiaomi MiMo-V2.6-Pro fixes 22.7% of 105 real bugs for just $0.86 in blind test — PawelHuryn · 2026-09-22
• Xiaomi MiMo-V2.6-Pro fixes real bugs at $0.86, carving out a strong Pareto frontier — PawelHuryn · 2026-09-22
• Bug Hunt Bench tests frontier coding models on 105 real bugs, costs vary 200x — PawelHuryn · 2026-09-22