Commit History
12 days ago
-
Leaderboards and model pages show the Arena Score with rank ranges
- Leaderboards on the front page and challenge pages rate models by the Arena Score with its 95 % confidence interval, as a point and a probabilistic view, with the rank shown as a range - Models with too few weeks of results or too little coverage show that status in place of the rank - MASE (30 days) and SQL (30 days) replace the average columns - Model pages plot the Arena Score history with its interval and rank range - About page and track explanation describe the Arena Scoreb7bd457
27 days ago
-
Show each model's track (Reference or Open) on the leaderboards and model pages, with a switch to view one track
746d216
-
Render the model detail page when metadata is missing
Model size was formatted unconditionally, so a model registered without one crashed the page into the error boundary. Every optional field now falls back to "Not specified", and a missing publishing date no longer reads as 1970. Sub-requests are also settled individually, so an unranked model still shows its details instead of failing the whole page.8ab8627
-
Show the scaled quantile loss beside ELO and MASE, and hide flat forecast bands
085fae4
-
Remove the Models tab and its hand-maintained model descriptions
796af1d
-
responsive container padding; stop hiding horizontal overflow
f26d4d4
-
feat(models): Models tab + active challenge rounds (rebuilt off main)
Sascha Kaltenpoth +1: Claude Opus 4.8 (1M context)Fresh dev branched from origin/main carrying only the model-related work from the old dev; every other dev feature is intentionally left at main. Kept: - Models nav tab + per-family pages and content (#3) - GET /models strict readable_id lookup + paper/repo/website/description metadata "Resources" panel on the model detail page (#33, backend #43) - VisionTS family pointed at VisionTS++ paper/repo - Active challenge rounds on the model overview page (#26) Reverted to main (dropped from this branch): - News/blog section (#31), mobile burger menu (#34), About/LinkedIn (#22), rankings/About reorder (#18), prediction step count (#14), quantile-band caption (#19), challenge sort (#27), leaderboard error states (#28), status explanations (#9), duplicate Recent dropdown fix The full original dev history is preserved on branch dev_old. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>0fdf0b2
-
feat: clarify hourly evaluation vs monthly reporting in info boxes (#25)
f36bbb5
-
clean up code
Henrik Albersfd7d5fa
-
clarify model size
Henrik Albersd12c223
-
convert to next.js
Henrik Albers42f149e