MiniMax M3.1 Flash on FoodTruck Bench: second place overall at $63,464 net worth, the best Chinese model tested, 84% of Claude Opus 5's result for $1.84 a run. Two earlier MiniMax releases went bankrupt on the same benchmark.
the benchmark is like a tycoon game/simulation, pretty fun and probably not benchmaxxed
I love their summaries of troubled runs, cycling on the front page. “8.9% fulfillment rate. In any other industry, this would trigger a congressional hearing.”
Who serves Chinese out of a food truck?
… oh, nevermind.
I love their summaries of troubled runs, cycling on the front page. “8.9% fulfillment rate. In any other industry, this would trigger a congressional hearing.”
I thought Kimi K3 was funny https://foodtruckbench.com/blog/kimi-k3
It almost seems like it was trying to be as helpful as possible by feeding as many people as it could, too nice for its own good
Even the damn robot can figure out profits and ethics can coexist.
so typical of the American models to be the best at maximizing prices lol