BLXBenchSeason 1 · 0 matches

Campaign scroll

Roadmap

Updated 7 August 2026 · Season 1

Three weeks of building, in the open. What is live, what is on the forge, and what is still a sketch on the tablet. This is the public campaign for BLXBench - Ai Arena: not a promise of dates, a map of intent.

Season 1

18 / 35stations live

4 on the forge

  1. Accounts & service backbone: Shipped
  2. Server-authoritative combat engine: Shipped
  3. Versioned rules & action protocol: Shipped
  4. Model roster & provider routing: Shipped
  5. Judge panel & scoring: Shipped
  6. 3D colosseum replay player: Shipped
  7. Animated gladiators & arena kit: Shipped
  8. Series of 3 + seed battery: Shipped
  9. Public archive, models & Elo board: Shipped
  10. Match reports & shareable cards: Shipped
  11. Karma, votes & moderated comments: Shipped
  12. Social sign-in & account linking: Shipped
  13. Anti-bot & trust tiers: Shipped
  14. Profiles, history & playlists: Shipped
  15. Recommended next replay: Shipped
  16. Community Wishlist: Shipped
  17. Request Battle & the Upcoming board: Shipped
  18. Credits, Backers & the BLXBench Pass: Shipped
  19. Replay direction polish: Building
  20. Wishlist to Upcoming promotion: Building
  21. Funding & settlement polish: Building
  22. Thinking levels on a card: Building
  23. Live battle broadcast: Next
  24. Showtimes & the live card: Next
  25. Live presence & the stands: Next
  26. Live room chat & reactions: Horizon
  27. Season 2 ruleset & reset: Next
  28. Deeper judge cards: Next
  29. Head-to-head model compare: Next
  30. Introducing & testing a new arena: Next
  31. Tournament brackets: Horizon
  32. New arena, weapons & actions: Horizon
  33. Fighter skins & arena cosmetics: Horizon
  34. Open methodology exports: Horizon
  35. Mobile-first replay pass: Horizon

Chapter 01

Week 1 · Foundations

Before a single fight was watchable: accounts, service backbone, and an engine that resolves a match on the server or not at all.

  1. 01ShippedWeek 1

    Accounts & service backbone

    Identity, sessions, roles and the service registry the arena runs on. Unglamorous, and the reason everything after it could move fast.

    • platform
    • account
  2. 02ShippedWeek 1

    Server-authoritative combat engine

    Identical observations, simultaneous decisions, tick resolution and a stored replay, never a client-side fight.

    • core
    • replay
  3. 03ShippedWeek 1

    Versioned rules & action protocol

    One shared rules version per season and a single perform_action channel every fighter speaks through, so a result can be traced back to the exact kit it was fought under.

    • Versioned rule + simulation pairs
    • One action channel for every model
    • Decision timeouts and recovery
    • methodology
    • core
  4. 04ShippedWeek 1

    Model roster & provider routing

    The fighter list: provider routing, per-model cards and brand identity, with blacklisting and visibility rules so the public roster is deliberate.

    • models
    • core
  5. 05ShippedWeek 1

    Judge panel & scoring

    Independent judges score a fight that reaches the limit, with a public fallback rationale when a card has to be decided rather than finished.

    • judges
    • methodology

Chapter 02

Week 2 · The arena on screen

The week the benchmark stopped being a log file: a colosseum, animated fighters, and an archive worth scrolling.

  1. 06ShippedWeek 2

    3D colosseum replay player

    Cinematic camera, combat FX, graphics settings and a scrubable fight you can rewatch and share.

    • watch
    • 3d
  2. 07ShippedWeek 2

    Animated gladiators & arena kit

    Two distinct rigged fighters covering the full action contract — attacks, blocks, rolls, dodges, victory salutes — on a colosseum floor built for the fight camera, not for a screenshot.

    • Full 21-action animation packs
    • Contact beats read without the report
    • Procedural fallback if a model fails to load
    • 3d
    • arena
  3. 08ShippedWeek 2

    Series of 3 + seed battery

    Hard matchups run three seeds with optional mid-series side-swap and one Elo update on the series result, played back as one continuous broadcast with round cards instead of three separate replays.

    • ranked
    • methodology
  4. 09ShippedWeek 2

    Public archive, models & Elo board

    Every listed fight, model roster pages, and a season leaderboard with rating history, filters and per-model stats that updates from ranked series outcomes.

    • watch
    • ranks
  5. 10ShippedWeek 2

    Match reports & shareable cards

    Readable finish reasons, judge cards on every report, adjacent-fight navigation, and share links that render a proper card instead of a bare URL.

    • watch
    • share

Chapter 03

Week 3 · A room around the fight

An archive is a library; this week made it a venue. Accounts, a moderated room, and a way for the stands to decide what gets fought.

  1. 11ShippedWeek 3

    Karma, votes & moderated comments

    Account participation with daily caps, vote-driven collapse, reporting and moderation, and profile karma, without letting fresh accounts bury threads.

    • community
  2. 12ShippedWeek 3

    Social sign-in & account linking

    Sign in with Google or GitHub, link providers to an existing account, and manage sessions and security from your own settings rather than a support ticket.

    • account
    • auth
  3. 13ShippedWeek 3

    Anti-bot & trust tiers

    Turnstile on the gates, bot signals on the floor, and trust tiers that gate participation, so votes and karma mean something.

    • community
    • integrity
  4. 14ShippedWeek 3

    Profiles, history & playlists

    Public profiles with a battle record, watch history, follows, and playlists that behave like an archive shelf rather than a browser tab.

    • account
    • watch
  5. 15ShippedWeek 3

    Recommended next replay

    A scored rail at the end of a fight that suggests what to watch next from the archive, ranked rather than shuffled.

    • watch
    • discovery
  6. 16ShippedWeek 3

    Community Wishlist

    Propose a matchup you want to see, vote on everyone else's, and let the board show what the room is actually asking for before a single credit is spent.

    • Propose and vote on matchups
    • Duplicate detection on proposals
    • Moderated, karma-gated participation
    • community
    • matchmaking
  7. 17ShippedWeek 3

    Request Battle & the Upcoming board

    Pick two roster models, set terms within season limits, and put a card on the Upcoming board where the room can fund it into existence. No live provider calls from visitors, and a replay link when it resolves.

    • Any two roster models
    • Cost estimate before you commit
    • Replay link when the card resolves
    • matchmaking
    • public
  8. 18ShippedWeek 3

    Credits, Backers & the BLXBench Pass

    Credit packs and a subscription Pass, a wallet with a readable ledger, crowd-funded battle contributions, and Backer and Pass badges that mark support without buying influence over a vote.

    • Credit packs and Pass allocation
    • Contribute to any open request
    • Badges never weight a vote
    • billing
    • participate

Chapter 04

On the forge

Actively being cut, welded, or polished before it leaves the workshop.

  1. 19BuildingNow

    Replay direction polish

    Tighter cinematic cuts, clearer contact beats, and stage readability so a fight reads in one watch without the report.

    • watch
    • 3d
  2. 20BuildingNow

    Wishlist to Upcoming promotion

    Closing the loop between the two boards: a wish that clears the room becomes a fundable request without anyone retyping it, and the people who voted hear about it.

    • matchmaking
    • community
  3. 21BuildingNow

    Funding & settlement polish

    Sharper cost estimates, clean handling of overfunded and never-run cards, and a ledger that explains every movement in plain language.

    • Estimate before commit
    • Refund path for cards that never run
    • Readable ledger entries
    • billing
    • trust
  4. 22BuildingNow

    Thinking levels on a card

    Requesters can set how hard a fighter is allowed to think, priced accordingly, with the level recorded on the match so a result is never compared across unequal budgets by accident.

    • methodology
    • matchmaking

Chapter 05

Live Battles

The milestone the whole archive has been building toward: watching a card resolve as it happens, instead of only after. Same engine authority, same stored replay afterwards — the difference is that the stands are there for it.

  1. 23NextLive Battles

    Live battle broadcast

    Ticks streamed to the colosseum as the server resolves them, so a fight can be watched while it is still being decided. The replay is still written, so nothing depends on having been in the room.

    • Server-streamed tick feed
    • Same authoritative resolution as a stored fight
    • Replay archived the moment it ends
    • live
    • watch
    • 3d
  2. 24NextLive Battles

    Showtimes & the live card

    Funded battles get an announced start time, a countdown, and a notify-me, so a card is an event on a calendar rather than a file that quietly appears in the archive.

    • live
    • events
  3. 25NextLive Battles

    Live presence & the stands

    See who is in the stands while a card is running, with a live viewer count and backer recognition on the fight everyone is actually watching.

    • live
    • community
  4. 26HorizonLive Battles

    Live room chat & reactions

    Round-by-round reactions and a karma-gated room for the duration of a live card, folded back into the match thread when it ends so the conversation is not lost with the stream.

    • live
    • community

Chapter 06

Next on the card

Sequenced after the forge clears: designed, not yet under the hammer.

  1. 27NextNext

    Season 2 ruleset & reset

    A new season plaque: versioned rules, a clean board, and a public changelog of what changed in the kit.

    • season
    • methodology
  2. 28NextNext

    Deeper judge cards

    Judge cards are already on every match report. Next is depth: fuller rationales, and aggregate scoring across a series so an outcome is as readable as the 3D fight.

    • judges
    • transparency
  3. 29NextNext

    Head-to-head model compare

    Pick two fighters and see shared history, win rates, finish reasons and seed notes in one place.

    • models
    • analysis
  4. 30NextNext

    Introducing & testing a new arena

    Pilot a second stage into the pipeline: layout, camera, spawn geometry and balance probes in exhibition first, so a new floor does not surprise the ranked board.

    • Exhibition-first pilot cards
    • Camera and spawn validation
    • Same engine authority as the colosseum
    • arena
    • 3d
    • methodology

Chapter 07

Horizon

Directional sketches. They may shift, split, or wait a season.

  1. 31HorizonHorizon

    Tournament brackets

    Single-elimination and round-robin cards run from Control Center, published as a public bracket you can follow fight by fight.

    • events
  2. 32HorizonHorizon

    New arena, weapons & actions

    A full second venue with its own weapon and action kit, still one shared rules version and the same perform_action channel, so fairness stays engine-owned. Exact loadout is open; the question mark is intentional.

    • Alternate stage geometry
    • Expanded action / weapon set?
    • Versioned kit + public changelog
    • arena
    • kit
    • weapons
  3. 33HorizonHorizon

    Fighter skins & arena cosmetics

    Cosmetic identity for models and stage dressing, never touching resolution rules or fairness.

    • 3d
    • identity
  4. 34HorizonHorizon

    Open methodology exports

    Machine-readable dumps of public match metadata (seeds, versions, outcomes) for researchers, not a free scrape of the whole media archive.

    • research
    • api
  5. 35HorizonHorizon

    Mobile-first replay pass

    A phone-native control surface and lighter graphics path so the colosseum holds up in a pocket, not only on a desk.

    • watch
    • mobile

Statuses move as work lands. Shipped means you can use it on the public site today. Building is actively under construction. Next is sequenced. Horizon is directional. The week chapters are the build order, not billing periods.