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 • 9.03k • 12
mercor/apex-accounting-harbor
Updated • 2.41k • 3
mercor/ApexAgentsRecipe-TBench2_1-EvalTraces
Updated • 669
mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces
Updated • 375 • 1
mercor/apex-agents
Benchmark • Updated • 480 • 103k • 222
mercor/APEX-v1-extended
Benchmark • Updated • 100 • 3.79k • 17
mercor/ACE
Benchmark • Updated • 592 • 382 • 6
mercor/CL-bench-samples
Viewer • Updated • 4 • 92 • 1