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/ApexAgentsRecipe-TBench2_1-EvalTraces
Updated • 100
mercor/ApexAgentsRecipe-ApexAgents480-EvalTraces
Updated • 93
mercor/apex-accounting
Viewer • Updated • 10 • 870 • 3
mercor/apex-agents
Benchmark • Updated • 480 • 94.9k • 170
mercor/APEX-SWE
Updated • 6.6k • 26
mercor/APEX-v1-extended
Benchmark • Updated • 100 • 1.17k • 16
mercor/ACE
Benchmark • Updated • 592 • 165 • 6
mercor/CL-bench-samples
Viewer • Updated • 4 • 18 • 1