Commit History

  1. chore: update repo URLs after transfer to TIGER-AI-Lab/ClawBench Running

    Verified signature
    14447e5

  1. UI: default to V2 Hermes (single harness) + add Reset button to mirror website headline view

    Verified signature
    74fbf87
  2. leaderboard: render Cost / task column (avg per-task USD)

    Verified signature
    7ead7b7
  3. docs: re-apply TABLE_INTRO grammar fix (lost in concurrent revert)

    AgPerry
    ba965ff
  4. fix: sort leaderboard by Reward (lenient) DESC (was: preserve CSV order)

    Verified signature
    d921761
  5. fix: preserve CSV row order in leaderboard (matches website ranking)

    Verified signature
    e29739e
  6. docs: fix TABLE_INTRO grammar after lenient/strict split; mark Reward (lenient) as default sort key

    AgPerry
    bbb0385
  7. feat: split Reward into lenient/strict columns + render both

    Verified signature
    78eb1d2
  8. feat: default-sort leaderboard by Reward DESC⁠

    Yuxuan Zhang
    3835b02
  9. fix: auto-refresh leaderboard from dataset on every page load (no module-level cache)

    Yuxuan Zhang
    72e98ec

  1. V2: switch to raw Intercepted DESC sort + Hermes-only filter (visible-column order)

    Verified signature
    a036d16

  1. Add arxiv:2604.08523 tag for HF Papers auto-linking

    Verified signature
    50a75ee
  2. Sync Space INTRO+TABLE_INTRO+citation: Intercepted is sort key, full author list in BibTeX

    Verified signature
    a478c75
  3. Switch sort key to corpus-interception (Stage 1) with corpus-reward as tiebreak

    Verified signature
    e77a483
  4. Sort by corpus reward (passed/full_corpus_size) so partial batches don't outrank complete ones

    Verified signature
    78cfa0c
  5. Upload folder using huggingface_hub

    Verified signature
    41e181d
  6. initial commit

    Verified signature
    dbb3bdb