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

- dataset:
    id: open-agent-leaderboard/results
    task_id: overall
  value: 0.3796
  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: 0.07
  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: 0.26
  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: 0.5253
  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: 0.6
  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: 0.68
  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: 0.71
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: GPT-5.2'