gemini-4IMAGE
Gemini 4 Argon hits 27x speedup on KernelBench-Mega before its own request trips the safety filter
Argon [high] wrote a one-launch Kimi-Linear Decode megakernel for RTX PRO 6000 at 27.0x the PyTorch baseline, third of 35 behind Opus 5.5 and Sonnet 5.5, and the session ended mid-profiling when its own request was blocked by Gemini's safety filter.
Elliot Arledge
@elliotarledgeArchived 21 days agoOriginally posted 2026.10.14
Elliot Arledge @elliotarledgeOriginally posted 2026.10.14
Gemini 4 Argon [high] on KernelBench-Mega: It wrote a one-launch Kimi-Linear Decode megakernel for RTX PRO 6000 at 27.0x the optimized PyTorch baseline, 3rd of 35, behind Opus 5.5 (35.5x) and Sonnet 5.5 (32.1x). Gemini 3.8 Flash scored 2.7x here. For three hours it climbed the same curve as Sonnet 5.5. Then the session ended mid-profiling, when one of its own requests was blocked by Gemini's safety filter.
x.com/elliotarledge/status/2110370046308679895Archived 2026.10.15 11:34