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 8
mercor/apex-agents-v1.1
Viewer • Updated • 240 • 2.69k • 9
mercor/apex-accounting-harbor
Updated • 1.39k • 3
mercor/ApexAgentsRecipe-TBench2_1-EvalTraces
Updated • 776
mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces
Updated • 207 • 1
mercor/apex-agents
Benchmark • Updated • 480 • 40.7k • 219
mercor/APEX-v1-extended
Benchmark • Updated • 100 • 3.24k • 17
mercor/ACE
Benchmark • Updated • 592 • 307 • 6
mercor/CL-bench-samples
Viewer • Updated • 4 • 36 • 1