# Beating Anthropic's Original Performance Take-Home Challenge

> 1,361 cycles, down from a 147,734-cycle baseline, with no background in kernel optimization, SIMD, or compiler work.

- Author: Andrei Moise
- Published: 2026-08-20
- Category: Agentic Workflows
- Canonical: https://andreimoise.ai/blog/108x-speedup-anthropic-performance-takehome

Earlier this year, I took Anthropic's Original Performance Take-Home with no background in kernel optimization, SIMD, or compiler work.

Result: 1,361 cycles, down from a 147,734-cycle baseline (108.5×), passing all 9 published thresholds.

How? I asked questions, used agentic search, switched models, and applied different techniques.

## The search loop — branch → measure → prune → deepen

Tree-of-thoughts-shaped exploration over candidate optimizations. Another idea began with self-consistency but evolved into exploration. Seven parallel sessions with the same prompt, then comparing investigations, branching on candidates, measuring cycles, and pruning failures.

I switched models when plateaued (Claude ↔ Codex ↔ external GPT analysis). Different training data and post-training will result in different blind spots.

I also used agentic search to find what others did, how and why.

Caught them cheating. Once outright test edits, once semantic cheating that only a clean-room re-test exposed.

## Two lessons

Don't avoid problems where you lack expertise; AI can compensate. Be careful what you prune; don't outsource judgment, problem-solving, and understanding all at once.

We can outsource some of it, some of the time, not all of it at once. The skills we cut are our own.

## References

- https://github.com/anthropics/original_performance_takehome
- https://github.com/Neuronspeeed/Anthropic-Original-Performance-Take-Home-Challenge
- Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity (METR): https://arxiv.org/abs/2507.09089
- Do Users Write More Insecure Code with AI Assistants? (Perry, Srivastava, Kumar, Boneh — Stanford, ACM CCS 2023): https://dl.acm.org/doi/10.1145/3576915.3623157