# Artificial Analysis 62 Hacker News commenters recommended Artificial Analysis and 46 criticized it, November 2025 to November 2026. It was recommended in 11 of 13 months. **Verdict:** Runs standardized tests on AI models and combines results into comparable intelligence, cost and speed charts. Critics say its weighting and biases shape rankings. ## Why people recommend it - Cost and speed versus intelligence charts (7 comments): "I recommend looking at the "Intelligence vs. Cost to Run Artificial Analysis Intelligence Index"" ([source](https://news.ycombinator.com/item?id=47985381)) "benchmarks that include speed across many models and providers available at various places" ([source](https://news.ycombinator.com/item?id=48564592)) "Personally I do trust them, but I mainly look at the Intelligence Index vs. Time per Task" ([source](https://news.ycombinator.com/item?id=50216772)) - Many benchmarks combined in one place (5 comments): "The most popular with broad coverage of a range of benchmarks is artificialanalysis.ai" ([source](https://news.ycombinator.com/item?id=50156938)) "AA seems to do a good job making a single number as representative as possible" ([source](https://news.ycombinator.com/item?id=49451453)) "They are the only site that really combines all benchmarks into a single place" ([source](https://news.ycombinator.com/item?id=50214303)) - Current frontier models and prices (4 comments): "Look up price versus intelligence for your favorite open model on artificial analysis" ([source](https://news.ycombinator.com/item?id=50323812)) "Artificial Analysis is usually a good resource to find current frontier AI models." ([source](https://news.ycombinator.com/item?id=50035104)) "check out LLM service prices on https://artificialanalysis.ai/" ([source](https://news.ycombinator.com/item?id=46195744)) - Independent testing instead of lab claims (3 comments): "consistently running standardized benchmarks for LLMs, rather than just aggregating unverified claims from the AI labs" ([source](https://news.ycombinator.com/item?id=46978763)) "a solid and independent, though also to be fair somewhat imperfect source for a general overview" ([source](https://news.ycombinator.com/item?id=46808636)) "this is the whole raison d'etre for independent testing, like https://artificialanalysis.ai" ([source](https://news.ycombinator.com/item?id=48848994)) ## What people warn about - Inconsistent model inclusion and timing (4 comments): "Artificialanalysis should have a policy of only including available models or something." ([source](https://news.ycombinator.com/item?id=50277212)) "some models are on the leaderboard second they're released while others come days later" ([source](https://news.ycombinator.com/item?id=50149252)) "Also ArtificialAnalysis drop older foundational models to make room for new ones." ([source](https://news.ycombinator.com/item?id=49574166)) - Biased or opaque methodology (4 comments): "Artificial Analysis has some very specific biases or perspectives on what they are measuring, so I wouldn't take their benchmarks as the final word on model quality." ([source](https://news.ycombinator.com/item?id=50016738)) "I don't trust these Artificial Analysis indexes and I'm not sure why anyone considers them authoritative" ([source](https://news.ycombinator.com/item?id=50214165)) "treat AA results as just a data point and not the overarching 'authority' they may intend to be." ([source](https://news.ycombinator.com/item?id=50306287)) - Missing higher reasoning effort levels (3 comments): "the reasoning efforts are available for the Intelligence Index, but not the Coding Agents benchmark I was interested in" ([source](https://news.ycombinator.com/item?id=50302253)) "it's really unfortunate that artificial analysis only provides comparison at the highest reasoning level" ([source](https://news.ycombinator.com/item?id=50108986)) "I wish AA benchmarked the models at the reasoning efforts people actual use them at." ([source](https://news.ycombinator.com/item?id=50302088)) - Chart and ranking display errors (3 comments): "it's irresponsible for them to put the points on the chart if they don't have the correct values for one of the axes yet" ([source](https://news.ycombinator.com/item?id=50005796)) "Why does the top card say "Intelligence #1/173" when the bar chart further down shows it only at position 7?" ([source](https://news.ycombinator.com/item?id=49452108)) "they lower the bars of tied scores so on the site it looks like Astra in second place" ([source](https://news.ycombinator.com/item?id=49649694)) ## Alternatives hackers 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 - [GenAI Showdown](https://hackerapproved.com/p/genai-showdown.md): 9 recommend ## Where to get it - [Visit the official site](https://artificialanalysis.ai/) ## Cite as Hacker Approved, "Artificial Analysis", https://hackerapproved.com/p/artificial-analysis/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).