# Artificial Analysis Intelligence Index

8 Hacker News commenters recommended Artificial Analysis Intelligence Index and 49 criticized it, November 2025 to November 2026. It was recommended in 3 of 13 months.

**Verdict:** People cite it as one summary score across many benchmarks, and some call it the least terrible ranking of models. The common caveat is that critics say its weighting and updates shift rankings and that many of its benchmarks are now private.

## Why people recommend it

- Summarizes many benchmarks into one score (2 comments): "It's appealing to me because it's not just one benchmark but a summary of a collection of benchmarks." ([source](https://news.ycombinator.com/item?id=50214257)) "it is a mix of coding and knowledge" ([source](https://news.ycombinator.com/item?id=49574729))
- Seen as best ranking so far (2 comments): "I think it's best ranking of models so far" ([source](https://news.ycombinator.com/item?id=50277271)) "the AA one is the least terrible" ([source](https://news.ycombinator.com/item?id=50289159))

## What people warn about

- Rankings swing with each weighting update (5 comments): "Each time they update their ranking algorithm, the closed models from US labs jump up and any previously high ranking open model jumps down." ([source](https://news.ycombinator.com/item?id=50289124)) "AA immediately made an update to their index calculation that made it lose the top spot. It was very suspicious." ([source](https://news.ycombinator.com/item?id=50281265)) "The way Artificial Analysis keeps changing their weights feels kind of like deciding who the winner should be" ([source](https://news.ycombinator.com/item?id=49799194))
- Benchmarks miss real model strengths (4 comments): "most of their benchmarks are either not a representation of model strengths enough or they are not doing a good job of showcasing it properly" ([source](https://news.ycombinator.com/item?id=49572258)) "the Artificial Analysis intelligence index is not considered a good metric for intelligence anymore" ([source](https://news.ycombinator.com/item?id=49821855)) "It still feels off. Probably because the benchmarks its based on aren’t measuring the right things." ([source](https://news.ycombinator.com/item?id=50290760))
- Private benchmarks can't be replicated (2 comments): "apeishly mimicking the features of rigor and methodology while avoiding any real accountability" ([source](https://news.ycombinator.com/item?id=49577747)) "60% of the benchmarks contributing to the AA index are now private, nobody can replicate them." ([source](https://news.ycombinator.com/item?id=50291128))
- Suspected bias toward large labs (2 comments): "They probably prefer being used by the deep-pocketed organizations that have access to Gemini 4 Carbon" ([source](https://news.ycombinator.com/item?id=50289765)) "I'm not saying that AA is definitely taking money from the big labs and changing the benchmark" ([source](https://news.ycombinator.com/item?id=50288958))

## Alternatives hackers recommend

- [Artificial Analysis](https://hackerapproved.com/p/artificial-analysis.md): 62 recommend
- [LMArena](https://hackerapproved.com/p/lmarena.md): 39 recommend
- [ARC-AGI](https://hackerapproved.com/p/arc-agi-3.md): 22 recommend
- [OCR Arena](https://hackerapproved.com/p/ocr-arena.md): 11 recommend
- [Bullshit Benchmark](https://hackerapproved.com/p/bullshit-benchmark.md): 9 recommend

## Where to get it

- [Visit the official site](https://artificialanalysis.ai/)

## Cite as

Hacker Approved, "Artificial Analysis Intelligence Index", https://hackerapproved.com/p/artificial-analysis-intelligence-index/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).