# Benchmarks: what I've logged

> Benchmarks comes up in 2 posts of my AI log, from October 2026 to October 2026, and each item below links to the primary source. The sources come from Mercor, filed under open weights, frontier and agents and coding.

## Items

1. **A benchmark map of the US economy** (Mercor, 16 Oct 2026): Maps 924 benchmarks onto 923 occupations and finds that 90 percent of US working hours go to tasks with little or no benchmark coverage. [Primary source](https://www.mercor.com/research/labor-index/benchmark-map) · [Post](https://heyaliasif.com/ai/2026-10-17-deepseek-v41-flash-quantum-circuits-code-review#item-5)

## Posts

- 2026-10-29 [AnySpeechRecognizer, ElevenLabs Cue, DAYJOB: Tax](https://heyaliasif.com/ai/2026-10-29-anyspeechrecognizer-eleven-cue-dayjob-tax)
- 2026-10-17 [DeepSeek V4.1 Flash, Claude's quantum circuits, and review at volume](https://heyaliasif.com/ai/2026-10-17-deepseek-v41-flash-quantum-circuits-code-review)

Canonical: https://heyaliasif.com/ai/topics/benchmarks