GLM 5.2 Performance Benchmarks

Discussion (12 Comments)Read Original on HackerNews

wongarsu•about 2 hours ago

It does really well on "AA-Omniscience Non-Hallucination Rate", far higher than DeepSeek, GPT 5.5 or Fable. I really like that benchmark because it's one of the few benchmarks that allows LLMs to elect not to answer if they are unsure and punishes them for trying to bullshit their way through the benchmark

andai•5 minutes ago

This implies that other benchmarks (for which every AI provider is optimizing?) are actively encouraging bullshitting?

hemkeshr•17 minutes ago

Local models are already useful today. The next milestone is getting this level of performance onto truly affordable hardware.

XCSme•about 1 hour ago

I also tested it[0]: quite similar to GLM 5, a few percent better, 30% faster and 50% more expensive.

[0]: https://aibenchy.com/?q=glm

XCSme•about 1 hour ago

PS: Just added a cool feature, so you can filter the leaderboard for multiple models at once, by using a comma, like: https://aibenchy.com/?q=glm,claude

lousken•about 1 hour ago

still 1/4 of the price of anthropic and openai models though

lanycrost•about 2 hours ago

It's always nice to see how open source models growing, hope we will have good performance with lower tier hardware some day.

theturtletalks•about 1 hour ago

I want to trust their benchmarks but when they have Muse Spark over GPT-5.5, it gives me pause.

sourcecodeplz•about 2 hours ago

still quite verbose at 140m output tokens, but this is on max thinking. high should do better.

ChrisArchitect•about 1 hour ago

Some more discussion: https://news.ycombinator.com/item?id=48567759

DeathArrow•about 2 hours ago

One or two more releases and they will reach Fable level.

vitalyan123•about 1 hour ago

by then there will be Fable 5.21, again 5% ahead of every other SotA while still only 500% the size.

GLM 5.2 Performance Benchmarks

⚡ Community Insights

Discussion (12 Comments)Read Original on HackerNews