.eval_results/open_agent_leaderboard_openai_aws_claude-opus-4-5.yaml

- dataset:
    id: open-agent-leaderboard/results
    task_id: overall
  value: 0.6633
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: appworld
  value: 0.7
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: browsecomp_plus
  value: 0.61
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: swebench
  value: 0.65
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_airline
  value: 0.72
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_retail
  value: 0.78
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_telecom
  value: 0.58
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Claude Opus 4.5'