catalog_version: 0.1
snapshot_date: 2026-09-13
benchmarks:
  - id: hle
    name: Humanity's Last Exam
    constructs: [expert_knowledge, reasoning, multimodal]
    status: watch
  - id: arc-agi-2
    name: ARC-AGI-2
    constructs: [abstraction, generalization, novel_rule_induction]
    status: active
  - id: swe-bench-verified
    name: SWE-bench Verified
    constructs: [software_engineering, repository_issue_resolution]
    status: watch
  - id: swe-bench-multilingual
    name: SWE-bench Multilingual
    constructs: [software_engineering, multilingual_programming]
    status: active
  - id: terminal-bench
    name: Terminal-Bench
    constructs: [terminal_use, agentic_execution]
    status: active
  - id: bfcl-v4
    name: Berkeley Function Calling Leaderboard V4
    constructs: [tool_use, function_calling, agentic_execution]
    status: active
  - id: tau3
    name: tau3-bench
    constructs: [tool_agent_user_interaction, knowledge, voice]
    status: active
  - id: osworld-2
    name: OSWorld 2.0
    constructs: [computer_use, multimodal_agent]
    status: active
  - id: browsecomp
    name: BrowseComp
    constructs: [web_research, browsing]
    status: active
  - id: metr-time-horizon
    name: METR Task-Completion Time Horizon
    constructs: [autonomy_horizon, reliability, software_tasks]
    status: active
  - id: gdpval-aa-v2
    name: GDPval-AA v2
    constructs: [professional_work, artifact_creation, agentic_knowledge_work]
    status: active
  - id: aa-briefcase
    name: AA-Briefcase
    constructs: [long_horizon_knowledge_work]
    status: active_private
  - id: automationbench-aa
    name: AutomationBench-AA
    constructs: [business_workflows, tool_use]
    status: active_private
  - id: scicode
    name: SciCode
    constructs: [scientific_reasoning, scientific_programming]
    status: active
  - id: mlperf-inference
    name: MLPerf Inference
    constructs: [inference_system_performance, efficiency]
    status: active