§ scores pending
KellyBench.
An environment for long-horizon sequential decision (bankroll). No public model scores are machine-retrievable yet — it will be ranked by discriminative power the moment they publish.
85.9-pt ROI spread but every model loses money — discriminates by degree of failure; negative metric not on the 0..1 scale
§ Work with us
Need one that still separates models?
When the public environment for your capability saturates, you can’t tell your models apart and you can’t train past it. We build private, contamination-resistant, verifiable-reward environments and evals on a hold-out set — designed to discriminate where the public ones no longer do.