evaluation / outputs

Commit History

  1. add CoAct traj and fix viz page

    c9f7744

  1. remove all the with hint result

    d786aec
  2. add llama-3.1 result

    fb96108
  3. rename OpenDevin to OpenHands

    adf5af2

  1. add 2nd run

    --global
    455affb

  1. add gpt-4o-mini result

    Xingyao Wang
    3d1d4f1

  1. Revert "add result from gpt-4o-mini"⁠

    Xingyao Wang
    12597ea
  2. add result from gpt-4o-mini

    Xingyao Wang
    3d406f5

  1. update the last missing instance

    Xingyao Wang
    1aaf82f
  2. update result from pr2489

    Xingyao Wang
    fc34a41

  1. remove keys

    Xingyao Wang
    77dbd55
  2. revoke keys

    Xingyao Wang
    a34dfe3
  3. add gpqa result

    Xingyao Wang
    804693c

  1. update v1.8 perf

    Xingyao Wang
    ec5bc65

  1. add result for v1.8 no-hint gpt4o

    Xingyao Wang
    bd3dee6

  1. add v1.8 result

    Xingyao Wang
    bb84cd4

  1. update results using new ver of swebench

    Xingyao Wang
    091b42e

  1. add claude-3.5 result

    Xingyao Wang
    1aa3b7d

  1. update old result w/ swe-bench latest harness;⁠

    Xingyao Wang
    68dee1f

  1. improved patch apply

    Xingyao Wang
    9071da3
  2. improved patch apply

    Xingyao Wang
    a4e8ae8

  1. add report field

    Xingyao Wang
    5abf617

  1. Add CodeAct 1.6 no hint

    Verified signature
    f47ed15

  1. feat: add gpqa results (#8)⁠

    Verified signature
    833a91e

  1. add result for codeact 1.6

    Xingyao Wang
    03f74db
  2. add gpt-4-1106 results for codeact swe

    Xingyao Wang
    bb237c5
  3. Merge commit 'edc3858a6ea5d0c7317b630024203af60e146b52'

    Xingyao Wang
    f55ef7f
  4. update all swebench lite

    Xingyao Wang
    78d8859
  5. Update outputs/miniwob/README.md

    Verified signature
    edc3858
  6. Update outputs/webarena/README.md

    Verified signature
    c89a626
  7. Create README.md

    Verified signature
    cfa8976
  8. Create README.md

    Verified signature
    c323f7b
  9. remove extra merged file

    Xingyao Wang
    29a3904
  10. add Mixtral

    Xingyao Wang
    4731bca
  11. update results for CodeActSWEAgent

    Xingyao Wang
    81fb631
  12. remove output merged for a new format

    Xingyao Wang
    77b13b9

  1. Delete outputs/webarena/BrowsingAgent/gpt-4o-2024-05-13_maxiter_15_N_v1.0/output.jsonl

    Verified signature
    7168c1c
  2. Delete outputs/webarena/BrowsingAgent/gpt-3.5-turbo-0125_maxiter_15_N_v1.0/output.jsonl

    Verified signature
    fe88798

  1. add webarena and miniwob results (#5)⁠

    liboxuanhk +1: frankxu
    Verified signature
    aa9fe42
  2. Add MINT results (#6)⁠

    liboxuanhk +1: ryanhoangt
    Verified signature
    764b1c5

  1. agentbench (#3)⁠

    Verified signature
    e7273a2
  2. humanevalfix (#4)⁠

    Verified signature
    9535215

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

    xingyaoww +1: ryanhoangt
    Verified signature
    054cb87

  1. update results

    Xingyao Wang
    fe6c7e5

  1. add results for deepseek chat v2

    Xingyao Wang
    126490f
  2. add codeact swe agent

    Xingyao Wang
    9b33edf

  1. add gpt4o result for 1.5

    Xingyao Wang
    5dbfa12
  2. move data to swe_bench_lite

    Xingyao Wang
    23df10d

  1. rename dir

    Xingyao Wang
    0d2d477
  2. add result for deepseek

    Xingyao Wang
    f07fb3e