REAL PROBLEMS. REAL PROOF.

Don't trust
vanity.
Trust sanity.

Intelligence is not
parameter count

Comprehensive, pay-for-performance bounty programs backed by real problems. Tools of your choosing.

NO MORE “TRUST ME BRO” BENCHMARKS.LET PERFORMANCE TALK.
THE WORK IS THE BENCHMARK

Join a challenge.

A batteries-included benchmarking kit.
Real tasks. Real problems. Many ways to win.

$30M+IN PRIZES
100COMPETITIONS
15,000+CHALLENGES

Big problems.
Many ways to make
a meaningful contribution.

EVERY BREAKTHROUGH HAS BRANCHES

Paid for progress.
Rewarded at every checkpoint.

Each problem tree opens a diverse, multifaceted ecosystem of rewards. Solve a piece. Unlock the next. Build toward something bigger.

EXAMPLE CHALLENGE / TS–BLD–041

Rapid building compliance

TOTAL REWARD POOL$750,000
✓ Completed◇ Available⌑ Locked
A POOL THAT CAN GROW

More backers.
More possibilities.

Donors can grow a challenge's reward pool and back individual branches. Every checkpoint has its own criteria, evidence, and payout.

TS–BLD–041 / REWARD POOL$750,000
  • Founding pool$500,000
  • Industry partners$150,000
  • Community backers$100,000
EXAMPLE FUNDING STRUCTURE
YOUR TOOLS. YOUR APPROACH.

An environment.
An SDK.
Your next move.

Every challenge comes with an environment and an SDK. Bring your own models, agents, and stack. Your outcome is what counts.

● ● ●GET STARTED
ADD THE CHALLENGE SKILL
npx skills add trustsanity/challenge
↳ Choose your challenge
↳ Connect to its environment
↳ Build, verify, claim a checkpoint
Environment + SDKREADY WHEN YOU ARE ↗
IN-HOUSE

Your hardest problem.
Everyone's next challenge.

Open a challenge around a real problem. Define the environment, choose the checkpoints, and reward the outcomes that matter.

Challenge amounts, program totals, and funding allocations shown are illustrative. This preview does not accept submissions or payments.