Overview table gets a row per variant, and its cost columns follow the row 17d9c9b Running LennartPurucker Claude Opus 5 commited on 2 days ago
Update leaderboard data + version history for ChimeraBoost 0.30.0 9b53220 LennartPurucker commited on 8 days ago
Per-dataset results leave out the models that could not run on a dataset 74c6c71 LennartPurucker Claude Opus 5 commited on 11 days ago
Selection bar stays down past the per-dataset section dcf9e02 LennartPurucker Claude Opus 5 commited on 11 days ago
Charts no longer draw themselves before they can be measured 5cf9f1a LennartPurucker Claude Opus 5 commited on 11 days ago
Systems as their own class of entrant, and per-dataset results 9a668d8 LennartPurucker Claude Opus 5 commited on 11 days ago
Refresh leaderboard data with the re-run EXAONE-Tabular results 3e8e748 LennartPurucker Claude Opus 5 commited on 13 days ago
Revert "Refresh leaderboard data with the re-run EXAONE-Tabular results" 32fa5a1 LennartPurucker commited on 13 days ago
Refresh leaderboard data with the re-run EXAONE-Tabular results d96dd98 LennartPurucker Claude Opus 5 commited on 13 days ago
fix: drop medals from the full leaderboard table, hold the dark theme dd9bac5 LennartPurucker Claude Opus 5 commited on 17 days ago
add: paper-view default, figure download, panel restyle c63e790 LennartPurucker Claude Opus 5 commited on 22 days ago
add: interactive leaderboard overview, paper view, US decimals 3b80af5 LennartPurucker Claude Opus 5 commited on 22 days ago
add: interactive explorer artifacts (html + csv data exports) 43646be LennartPurucker commited on 29 days ago
Auto-size explorer iframes and force their dark theme e62379f LennartPurucker Claude Fable 5 commited on 29 days ago
Stack interactive Pareto panels full-width 3d928f1 LennartPurucker Claude Fable 5 commited on 29 days ago
Embed interactive Pareto explorers with static-PNG fallback 96e822b LennartPurucker Claude Fable 5 commited on 29 days ago
Refactor leaderboard UI into modules and revamp content/styling 4d6fb4f LennartPurucker Claude Opus 4.8 (1M context) commited on Jun 23