Anthropic open-sourced its original performance take-home — the optimization test it used before Claude started beating humans at it. You are given a Python-simulated VLIW machine and a working but slow kernel in perf_takehome.py. Your job: rewrite build_kernel so the same computation finishes in as few clock cycles as possible.
This leaderboard began as a community project (the ant-challenge leaderboard) and now lives in the arena, with all standings preserved.
Community project — not affiliated with or endorsed by Anthropic.
The simulator is a wide-issue VLIW core: each cycle it dispatches one instruction bundle across parallel engines — alu, valu, load, store, and flow. Your Python code runs once to build the instruction stream; the machine then executes it. The score is how many cycles that execution takes. Keeping every engine busy every cycle is the whole game: scheduling, vectorization, software pipelining, and algebraic shortcuts all pay off.
perf_takehome.py. The judge runs the upstream correctness shape: forest_height=10, rounds=16, batch_size=256, output values required, output indices optional.Two reference scores from the upstream README appear directly in the rankings:
performance-recruiting@anthropic.com with your code.perf_takehome.py (at most 1,000 KB).Submissions are temporarily closed while the sandboxed (E2B) judge moves into the arena. The leaderboard preserves all standings from the original site and reopens for new entries once the judge port lands.
The take-home itself — simulator, starter kernel, and correctness tests — lives in anthropics/original_performance_takehome. Clone it and run python tests/submission_tests.py to check which thresholds you pass locally before submitting.