Season 6 pool: add Rose-Pro, Rose-Medium, DynamicMind-MoE, Er-Tiny-1.3M, Er-Medium-12.5M, Er-Large-30M

Season 6 pool: param counts for Rose-Pro, Rose-Medium, DynamicMind-MoE, Er-Tiny/Medium/Large

Org colours closer to each profile photo

Pool: LowOnMind-5M now from SLM-Archive

Play Style chart: collision-free labels with leader lines, hover names; org colours from profile photos

LowOnMind-5M moved to SLM-Archive

Keep LowOnMind-5M's Elo history when the repo moved to SLM-Archive

Sizes: - GODELEV/Rose-1.5-Medium; + Novi-AI/Novi-Micro-Base

Pool: - GODELEV/Rose-1.5-Medium; + Novi-AI/Novi-Micro-Base

Season 5: fresh leaderboard for the new pool

Sizes: - removed models; + SmolLM-135M, SmolLM2-135M, Rose-1.5-Medium, Rose-Mini, Boris-1.3-75M

Season 5 pool: - Supra-Mini-v5-8M, Supra1.5-50M-Base-exp, SupraGDN-5M, LowOnMind-1M, BananaMind-2.1-Unified, BananaMind-2-Mini, DynamicMind-MoE; + SmolLM-135M, SmolLM2-135M, Rose-1.5-Medium, Rose-Mini, Boris-1.3-75M

Season 5 pool: - Supra-Mini-v5-8M, Supra1.5-50M-Base-exp, SupraGDN-5M, LowOnMind-1M, BananaMind-2.1-Unified, BananaMind-2-Mini, DynamicMind-MoE; + SmolLM-135M, SmolLM2-135M, Rose-1.5-Medium, Rose-Mini, Boris-1.3-75M

README: drop stale mention of the old Elo vs parameters chart

README: removed pool models leave the leaderboard

Pool: + Wisp-5M, Wisp-15M, Veyra2-Blueberry-5M; - LowOnMind-300k, BananaMind-2-Micro (also off the leaderboard)

Sizes: + Wisp-5M, Wisp-15M, Veyra2-Blueberry-5M; - LowOnMind-300k, BananaMind-2-Micro

Leaderboard keeps only pool models

DedeProGames and DedeBckp in light blue

Load the Press Start 2P pixel font for the 8-bit boards

8-bit Tetris look: bevelled blocks, black well, grey frame, pixel font, NEXT box

Light-blue accent theme (was yellow)

Leaderboard: Play Style chart replaces Elo vs Parameters; light-blue accent

README: note where the ranked pool lives (rebuild after build error)

Add Veyra2-Apricot/Mango, Supra-Mini-v5-8M, SupraGDN-5M, Supra1.5-50M, Overaddicted-500K

Sizes for 6 new models

Add DedeProGames/GPT-U-20M to Match and Ranked

Add GPT-U-20M size

Remove raw completion code

Stop generating raw completions

Back to Model: "good move" +value under each board

Document ranked without size limit

Ranked: any sizes can meet (MAX_PARAM_GAP defaults to 0)

Ranked: no size limit by default (one Elo scale for all models)

Show the model's raw completion under each board

Record the model's raw completion for each played move

LMPlayer.complete: the model's raw greedy completion for the chosen move

Document the 100M+ rule

Season 4: fresh leaderboard for the new 22-model pool

Only 22 models (incl. BackKiyo-10M); 100M+ models play each other freely

Ranked: 100M+ models can all play each other; pool trimmed to 22 models

Add BackKiyo-10M size

Document Match and Ranked tabs

Season 3: fresh leaderboard for random ranked matches

Split Match (friendly) and Ranked (random models) tabs

Ranked matchmaking: random models, server-side matches

Document 50K minimum

Enforce 50K minimum model size

Drop models under 50K parameters from the leaderboard

Minimum model size: 50K parameters