FrontierPhysics scientific inputs. One repo per dataset; new names: frontierphysics-<task-id>. Pin full commit revisions.
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
datasets 12
benchflow/heat-assisted-detection-and-ranging
Updated
benchflow/frontierphysics-multiplexing-ion-chain-qnet
Viewer • Updated • 1
benchflow/skillsbench
Benchmark • Updated • 3.78k • 14
benchflow/skillsbench-leaderboard
Updated • 5.61k • 2
benchflow/benchmarks
Updated • 375
benchflow/skillsbench-research-artifacts
Updated • 10
benchflow/skillsbench-trajectories-apr2026
Updated • 449 • 1
benchflow/skillsbench-data
Viewer • Updated • 94.3k • 213
benchflow/ClawsBench
Viewer • Updated • 7.83k • 452 • 4
benchflow/artifacts
Preview • Updated • 14