.eval_results/open_agent_leaderboard_openai_azure_gpt-5.2-2025-12-11.yaml

- dataset:
    id: open-agent-leaderboard/results
    task_id: overall
  value: 0.4075
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: appworld
  value: 0.0
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: browsecomp_plus
  value: 0.46
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: swebench
  value: 0.57
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_airline
  value: 0.54
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_retail
  value: 0.73
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_telecom
  value: 0.53
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'