Checkpoints and eval traces from "Training frontier knowledge work agents: A 397B open recipe with SkyRL"
AI & ML interests
None defined yet.
Recent Activity
View all activity
datasets 9
mercor/OpenWorldEngineer
Viewer • Updated • 26 • 166
mercor/apex-agents-v1.1
Viewer • Updated • 240 • 10.9k • 13
mercor/apex-accounting-harbor
Updated • 2.59k • 3
mercor/ApexAgentsRecipe-TBench2_1-EvalTraces
Updated • 704
mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces
Updated • 496 • 1
mercor/apex-agents
Benchmark • Updated • 480 • 200k • 222
mercor/APEX-v1-extended
Benchmark • Updated • 100 • 3.43k • 17
mercor/ACE
Benchmark • Updated • 592 • 404 • 7
mercor/CL-bench-samples
Viewer • Updated • 4 • 108 • 1