Merged-page review fixes: exclude flagged rows, wire comparability, thread card c5c4016 j-chim Claude Fable 5 commited on 4 days ago
Route single-segment eval ids to the merged benchmark page (F2-F4) d20fb23 j-chim Claude Fable 5 commited on 4 days ago
Merge remote-tracking branch 'origin/main' into merge/main-into-v2-cleanup 6e90b4d j-chim commited on May 28
Add per-model + per-eval OpenGraph thumbnails; replace "EE/EC" mark with logo image c315a26 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 28
Untrack accidentally-committed noise files; gitignore the patterns 445ce35 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 28
view-data: paranoid CAST every output column to a primitive type b6dab21 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 28
Internal-feedback pass: rename to "Evaluation Cards", rework Summary view, simplify §4 metrics faa9b3f evijit HF Staff Claude Opus 4.7 (1M context) commited on May 27
Cross-suite signals, sortable leaderboard, theme cleanup 0314721 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 6
Cross-source dedup, plotbox polish, pretty URLs, eval page fallbacks 0b45710 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 6
Match nested benchmarks in /evals search; auto-expand families with hits 26f932a evijit HF Staff Claude Opus 4.7 (1M context) commited on May 6
Move reader-mode toggle to detail pages; theme banners + apples-to-apples 4629534 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 6
Merge cross-source benchmark families; tidy leaderboard panel + table chrome 8ef4cbc evijit HF Staff Claude Opus 4.7 (1M context) commited on May 6
Make /models tables column-sortable; rebalance /evals + /models toolbars 5a2d59c evijit HF Staff Claude Opus 4.7 (1M context) commited on May 5
Move split selector below the reporting comparison heading 629a612 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 5
Fix sort toggle direction and remove categories as sortable column c9c5a30 evijit HF Staff Claude Sonnet 4.6 commited on May 5
Sort evals list by family name; add sortable columns; use cleaned display names 919a75f evijit HF Staff Claude Sonnet 4.6 commited on May 5
Group model/eval-detail benchmarks by hierarchy.json families f073e7a evijit HF Staff commited on May 5
Wrap /evals page in Suspense for useSearchParams 3df9dfd j-chim Claude Opus 4.7 (1M context) commited on May 5
Consolidate hierarchy terminology + handle v2 hierarchy shape 350e866 evijit HF Staff commited on May 4
Tighten eval cards UI and clean up stale local data 32864b0 evijit HF Staff Claude Opus 4.7 (1M context) commited on May 3
Add new component files and align app to EvalEval design system dbdd6d1 evijit HF Staff Claude Sonnet 4.6 commited on May 3
Align user-facing labels with paper terminology 4be62f9 evijit HF Staff Claude Opus 4.7 (1M context) commited on Apr 30
Fix Fibble Arena (and similar) suite link routing c569d0f j-chim Claude Opus 4.7 (1M context) commited on Apr 29
Add interpretive signals, corpus dashboard, and slice browser bca888a evijit HF Staff Claude Opus 4.7 (1M context) commited on Apr 27
Improve eval/model UX, lite data paths, and leaderboard clarity 436ada0 evijit HF Staff commited on Apr 14
Add per-benchmark comparison histograms on model detail 415ac43 evijit HF Staff Claude Opus 4.6 (1M context) commited on Apr 13
evijit HF Staff Claude Opus 4.7 (1M context) commited on 
