Kimi K3 Ranks As Strongest Open Model On MathArena Leaderboard
Reactions from ranked influencers
3 posts
This is absurdly impressive. BrokenArXiv is *hard* for LLMs and OpenAI focused on such problems hard and holds a commanding lead. Kimi is not a frontend slop machine, it's a generalist proto-AGI (though same can be said of Meta, congrats)
We have added Kimi K3 and Muse Spark 1.1 to the MathArena leaderboard! Kimi K3 now ranks as the strongest open model at #5, behind GPT-5.6,5.5 and Fable.
K3 trying to prove impossible statements. Who was saying open models don't speak neuralese? This isn't yet Fable-dense, but this is already "grug speech" stage. Distillation on exfiltrated CoTs or convergence? you decide.