evaluation / utils

Commit History

  1. change test_result to bool

    Xingyao Wang
    1ae8615
  2. fix fine-grained report; support visualization while running

    Xingyao Wang
    7eb2653
  3. support visualization of new swebench-eval

    Xingyao Wang
    414a759

  1. Create visualization for MINT benchmark & upload results (#2)⁠

    xingyaoww +1: ryanhoangt
    Verified signature
    054cb87

  1. Merge commit 'f6d9f43457bdadd36685181efda2fd45e813a02c'

    Xingyao Wang
    d61638c
  2. visualize swe-bench-lite & fix stuck in look

    Xingyao Wang
    4deac19

  1. add cost info when exists

    Xingyao Wang
    f6d9f43

  1. show errrors

    Xingyao Wang
    565afe1

  1. fix glob

    Xingyao Wang
    3c245bf
  2. update visualizer on multi-page

    Xingyao Wang
    1412295

  1. change to only load merged

    Xingyao Wang
    3bf3aaa
  2. add absolute number of solved

    Xingyao Wang
    886e465
  3. add benchmark code

    Xingyao Wang
    edcb2c1
  4. support multi-page

    Xingyao Wang
    4e9c2f0