News for hackers. Stuff that matters.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by YuechenLi on Thursday November 19, 2026 @07:34PM (#50568617)
Ok, so I can see that this is a benchmark the submitter made and submitted themselves, which is kinda misleading and should at least be disclosed.

But my question is, what does this benchmark actually measure about the LLM's engineering abilities? It just looks like a page of random bar graphs to me.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by khimaros on Thursday November 19, 2026 @07:49PM (#50568740)
this seems to be a composite index based on TerminalBench, CursorBench, vals.ai, etc: https://github.com/git-aarvin/mei/tree/main/source/jsonc

looking at the graphic below the table, it does seem like data is missing for Neon which is present for Fable, and isn't penalized for the missing benchmarks.

Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by jeffbee on Thursday November 19, 2026 @09:11PM (#50569311)
Yeah that seems to be a huge caveat
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index by seizethecheese on Friday November 20, 2026 @12:08AM (#50570408)
Seems fair game to me if the benchmark were actually a reasonable attempt at rating models, but it’s total slop. Like Neon score is based on three benchmarks and Fable based on 6 and that’s hidden.