Sinatras(@myainotez):Time to give agents a hard task, introducing pmpp-hard! 69 GPU kernel tasks, 11 models, 3.1k agent rollouts and 5.8B+ tokens later we have the results. Kimi K3 claims the first place with a 0.71 score. Without dealing with if your task is “frontier” or not, it just solves them

Sinatras

@myainotez

Entropy Preservation Officer • AI/ML Engineer • RL Residency @PrimeIntellect

가입 May 2024

664 팔로잉 중 2.1K 팬

Sinatras@myainotez

2026.08.03 15:01

Time to give agents a hard task, introducing pmpp-hard! 69 GPU kernel tasks, 11 models, 3.1k agent rollouts and 5.8B+ tokens later we have the results. Kimi K3 claims the first place with a 0.71 score. Without dealing with if your task is “frontier” or not, it just solves them