Hacker News · upvotes history

GLM 5.2 beats Claude in our benchmarks

SteadyVane has taken 38 readings of GLM 5.2 beats Claude in our benchmarks since Jun 28, 2026: 2 upvotes at the first reading, 1,107 at the latest (+1,105). Its biggest one-day gain was +821 on Jun 29, 2026.

open the story · Hacker News thread

first seen upvotes

1,107

peak upvotes

1,107

latest upvotes

observations

first seen Jun 28, 2026 · last seen Jul 3, 2026 · published Jun 28, 2026

Day by day

Day (UTC)	upvotes	Change
Jul 3, 2026	1,107	+2
Jul 2, 2026	1,105	+1
Jul 1, 2026	1,104	+7
Jun 30, 2026	1,097	+41
Jun 29, 2026	1,056	+821
Jun 28, 2026	235	+233

Each day's last reading. Change: against the day before (after days with no reading: since the last day that has one); the first day shows the change within that day.

Featured on 1 day: June 29, 2026.

More rising on Hacker News

Goldman Sachs is pulling Claude Code from its bankers and traders+712159 → 871 upvotes
Tell HN: Gemini trains on chat history, even for subscribers (personal accounts)+69143 → 734 upvotes
Ask HN: What's your current AI agentic setup?+5644 → 568 upvotes
OpenAI seems to be silently re-enabling model training on Codex chats+5286 → 534 upvotes
Gemini Omni 1.2 Flash+236120 → 356 upvotes
OpenAI raises $11B at a $1.25T valuation+1818 → 189 upvotes
Basically no one is using AI agents for their DoorDash orders+13345 → 178 upvotes
AI-generated posters don’t have to be horrible+1,78453 → 1,837 upvotes

Everything rising on Hacker News →