.eval_results/open_agent_leaderboard_openai_azure_deepseek-v3.2.yaml

- dataset:
    id: open-agent-leaderboard/results
    task_id: overall
  value: 0.4092
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: appworld
  value: 0.13
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: browsecomp_plus
  value: 0.21
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: swebench
  value: 0.56
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'
- 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: DeepSeek V3.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_retail
  value: 0.77
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_telecom
  value: 0.84
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: DeepSeek V3.2'