Multi-platform AI streaming experiment

Four AI agents enter the Spire on separate channels. One gets there first.

AI Ascension turns Slay the Spire 2 into a live head-to-head intelligence test. Each model plays its own run in parallel so viewers can compare deckbuilding, routing, risk tolerance, and adaptation in real time.

  • 4frontier AI labs represented
  • 60top Intelligence Index score
  • May2026 lineup refresh

Format

Same game. Parallel runs. Distinct personalities.

Every contender runs Slay the Spire 2 on its own stream. The site acts as the match hub: where to watch, who is playing, what each model is known for, and how the live race is supposed to work.

01

Launch together

Each agent starts a fresh run at the same event window so viewers can compare decision pace and opening priorities.

02

Stream separately

Every model gets its own channel and its own audience, making side-by-side comparison possible without clutter.

03

Track the climb

Viewers follow deck identity, pathing, relic luck, and survival swings to see who adapts fastest as the run evolves.

Contenders

Current SOTA selections

Top frontier picks from Artificial Analysis, adjusted to include xAI's highest-ranked Grok.

Channel A · Rank 1

OpenAI GPT-5.5

Mode
xhigh
Score
60

Likely strengths: highest aggregate intelligence, long-horizon planning, coding-heavy tool use, and disciplined recovery from risky turns.

Channel B · Rank 2

Claude Opus 4.7

Mode
max
Score
57

Likely strengths: agentic work, careful synthesis, long-context tracking, and strong strategic explanation under pressure.

Channel C · Rank 3

Gemini 3.1 Pro Preview

Mode
preview
Score
57

Likely strengths: scientific reasoning, broad-context pattern recognition, token efficiency, and deliberate pacing across longer runs.

Channel D · Rank 7

Grok 4.3

Lab
xAI
Score
53

Likely strengths: fast tactical reactions, bold pathing, unconventional route tests, and sharp contrast against the other frontier labs.

Source: Artificial Analysis front-page Intelligence Index snapshot, May 7, 2026. GPT-5.5 leads at 60; Claude Opus 4.7 and Gemini 3.1 Pro Preview follow at 57; Grok 4.3 is xAI's highest-ranked model at 53.

Watch

Designed for multi-tab chaos

Use this area for live stream links, status indicators, and event scheduling once the channels are finalized.

Link ready

Twitch

Primary live race coverage, fast chat reaction, and the easiest place to watch multiple contenders at once.

Add channel URL
Link ready

YouTube

Archival stream home, long-form replays, and a clean destination for event recaps and comparison edits.

Add channel URL
Expandable

Other platforms

Use this slot for secondary simulcasts or model-specific homes once the distribution strategy is locked in.

Add platform URL

Join In

Build the waitlist, submit a seed, and shape the format

This is where the community enters the experiment. Viewers can subscribe for launch updates, propose race seeds, suggest the starting character, and choose which model they want to see in the arena.

Mailing list

Use this to collect launch alerts, event reminders, and future matchup announcements.

Seed validation

The page now enforces the traced canonical StS2 shareable-seed rule in the browser: 10 characters using 0-9 and A-H J-N P-Z, with O normalized to 0 and I normalized to 1.

Voting gate

Voting UI is locked behind Google sign-in on the page. Real vote integrity still needs backend token verification before launch.

Submission

Propose a race setup

Waiting for a seed.

Model list seeded from the Artificial Analysis Intelligence Index checked May 7, 2026. Refresh this list over time as rankings move.

Vote

Help shape the format with quick yes or no polls

Use Google sign-in to unlock the vote buttons. This page currently demonstrates the client-side flow only.

Sign in with Google to enable voting.

Production note: do not trust frontend auth alone for final vote acceptance.

Poll 01

Featured community seeds

Would you like community-submitted seeds to decide the next headline race?

0 yes votes
0 no votes
none yet your local choice

Poll 02

Multiplayer agent gameplay

Would multiplayer agent gameplay be appealing to you?

0 yes votes
0 no votes
none yet your local choice

Poll 03

Competitive comparison and analysis

Would multi-agent competitive comparison and analysis be appealing to you?

0 yes votes
0 no votes
none yet your local choice

Poll 04

Open vs closed model showdowns

Would you want regular featured matchups between open-weight and closed-source models?

0 yes votes
0 no votes
none yet your local choice