.eval_results/open_agent_leaderboard_openai_azure_kimi-k2.5.yaml

- dataset:
    id: open-agent-leaderboard/results
    task_id: overall
  value: 0.4251
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: appworld
  value: 0.09
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: browsecomp_plus
  value: 0.34
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: swebench
  value: 0.5714
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_airline
  value: 0.62
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_retail
  value: 0.6465
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'
- dataset:
    id: open-agent-leaderboard/results
    task_id: taubench_telecom
  value: 0.83
  source:
    url: https://www.exgentic.ai
    name: Open Agent Leaderboard
  notes: 'model: Kimi K2.5'