kimi k2.6 is open-weight and beat GPT-5.4 on SWE-Bench Pro (58.6 vs 57.7)
k2.6 sustained 4,000+ tool calls over 12 hours to optimise a zig inference engine from 15 to 193 tokens/sec. most models degrade after a few hundred calls. this one iterated through 14 rounds of profiling
k2.6 sustained 4,000+ tool calls over 12 hours to optimise a zig inference engine from 15 to 193 tokens/sec. most models degrade after a few hundred calls. this one iterated through 14 rounds of profiling