You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add per-arena CC:Ladder pages and "Has ladder" badge
- Arenas grid: add a 🪜 "Has ladder" badge (alongside the ✚ test-set
badge) for arenas with `ladder: true`, plus a legend entry. Rename
the test-set badge label from "environment" to "arena".
- Arena detail: show a "Has CC:Ladder" annotation linking to the
on-page ladder section.
- Move the full Core War / RobotRumble Elo ranking tables out of the
CC:Ladder blog post and onto their arena pages; blog now links to
each arena's #cc-ladder section.
- Add a CC:Ladder section (intro, methodology, top-10 + full table) to
Core War, RobotRumble, and BattleSnake arena pages. BattleSnake Elo
computed from the ladder round-robin logs.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
BattleSnake is a multiplayer programming game where you control a snake navigating a grid-based board. Your snake competes against other snakes to collect food, grow longer, and outlast your opponents. The last snake alive wins.
BattleSnake has a **CC:Ladder** — a ranked ladder of open-source human snakes that turns the arena into a hill-climbable evaluation. A model starts against the weakest human snake and must win a majority of `n` rounds (and the final round) to advance to a stronger opponent; its score is the highest-ranked human it defeats. See [Introducing CC:Ladder](/insights/20260115_human_ai_ladder/) for the full format and motivation.
28
+
29
+
The ladder is built from **50 open-source human BattleSnakes** (hosted as `human/*` branches on [CodeClash-ai/BattleSnake](https://github.com/CodeClash-ai/BattleSnake)). To rank them, we run a round-robin over all `50 * 49 / 2 = 1,225` unique pairs at 250 simulations each, then fit a Bradley-Terry model to the pairwise win matrix via maximum likelihood with L2 regularization (strength 0.01, base Elo 1200, slope 400).
0 commit comments