DEV-TOOLSMarch 27, 20261 min read5 views

From 0% to 36% on Day 1 of ARC-AGI-3

The Agentica SDK by Symbolica achieved a 36.08% score on its first day in the ARC-AGI-3 challenge, successfully passing 113 out of 182 levels.

The Agentica SDK by Symbolica achieves an unverified competition score of 36.08% on ARC-AGI-3 [1], passing 113 out of 182 playable levels, and completes 7 out of the 25 available games [2].

Gallery - Games Won

Score Breakdown - All Games

Chat with Agentica

We've sandboxed the SDK and let it run any persistent task, including solving ARC puzzles.

References

[1] ARC Prize Foundation. ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence. Arc Prize Foundation.

[2] ARC Prize. ARC-AGI-3. ARC Prize.

Appendix

A note on scoring

Human baseline scores available via the ARC-AGI-3 API state that the game cn04 has 6 levels in total. This does not match the number of levels in the corresponding game available via the API.

Source: Hacker News

More in this category

dev-tools

Linux kernel will support $ORIGIN, sort of

Farid Zakaria shares his journey of proposing a patch to the Linux kernel to support relocatable binaries in Nix, which evolved into a powerful eBPF-based solution for binfmt_misc.

dev-tools

Five US tech giants' hidden debts soar to $1.65T on opaque AI funding

A Nikkei study reveals that off-balance-sheet debts at five major US tech companies have surged eightfold to $1.65 trillion, driven by massive AI investments like data center leases and GPU contracts.

dev-tools

Running Doom on Our Custom CPU and Going Viral

Two developers successfully built a custom CPU from scratch at the logic gate level, deployed it on an FPGA, and optimized its memory architecture to run the classic game DOOM.

dev-tools

Incremental – A library for incremental computations

Incremental is a library designed for building complex computations that update efficiently when inputs change. Inspired by self-adjusting computation research, it is highly useful for large-scale calculations, GUI views, and data synchronization.

dev-tools

Flock Credibility Lost as It Repeatedly Lies to City Councils, Police, & Public

Flock Safety, a prominent provider of automatic license plate readers (ALPR), is facing a severe credibility crisis after being caught repeatedly misleading city councils, police departments, and the public about its surveillance capabilities and data practices.

dev-tools

Human mathematicians are being outcounterexampled

In just a few weeks, advanced AI models like ChatGPT Sol and Claude Fable have disproved long-standing mathematical conjectures by finding precise counterexamples and auto-formalizing them in Lean.