GLM 5.2 is nearly as accurate as a human book keeper

·Hacker News··

We benchmarked GLM 5.2, an open-weights AI model, on a real quarterly UK VAT return: 59 transactions, 68 minutes, $2.73 of tokens — and a net VAT position within 7 pence of the human-prepared return.

Read full article →

Related Articles

The glass backbone: Why the Army's logistics will break in the next war
baud147258 · Hacker News · 9h ago
US seeks cheaper hunter-killer drones after Iran destroys $1B worth of Reapers
rbanffy · Hacker News · 9h ago
No leap second will be introduced at the end of December 2026
ChrisArchitect · Hacker News · 8h ago
Postgres rewritten in Rust, now passing 100% of the Postgres regression tests
SweetSoftPillow · Hacker News · 16h ago
John Deere owners will get the right to repair equipment under FTC settlement
djoldman · Hacker News · 22h ago