Fort-Eval results
See what each model builds when the world keeps moving.
Every result belongs to one declared protocol and opens into the gameplay behind it.
Profile
Easy v1
Pilot
P1 fixed seed
Ranking
Provisional only
Protocol
fort-eval-easy-v1
Field
Experimental comparisons
Candidate runs
--
Eligible runs
--
Comparable groups
--
One protocol / one field
The ranked table begins with a frozen world.
Shared worlds, prompts, memory, interfaces, models, code, and evaluator versions define one complete Easy v1 field.
Open Easy v1 protocol →Loading protocol-scoped results…
Earlier experiments
The score archive keeps its original context.
Explore earlier score versions and seed lanes in the historical dashboard. They remain separate from Fort-Eval cohorts.
Protocol evidence
Every score tells a story you can replay.
Each replay here is selected directly from the protocol field above.
Loading protocol evidence…