Remix.run Logo
▲ anon373839 2 hours ago

AA has become pretty meaningless. They just keep adjusting the recipe to get a preferred ranking result, with no supporting evidence for their decisions.

Edit: In addition to reshuffling the weighting of individual benchmarks, they also do things like test Anthropic and OpenAI in their native harnesses, while not doing the same for Qwen/Deepseek/etc.

▲the_duke 2 hours ago | parent | next [-]

To be fair, a lot of the popular benchmarks have become pretty meaningless.

Models often get great scores despite being a lot worse than the frontier in practice.

▲anon373839 19 minutes ago | parent [-]

This is true, but if you look at the change in weighting to specific benchmarks from one version of AA to the next, it looks really arbitrary.

▲gr_norm 2 hours ago | parent | prev | next [-]

Yeah, I don't know why people bother with it anymore. It no longer reflects what you're likely to see in real-world usage, at least IME.

▲stratts 2 hours ago | parent | prev [-]

One thing I find confusing about AA is that they show GPT 6.1 dominating the lower end of the Pareto line, with eg, GPT 6.1 Sol at medium supposedly costing far less per task than DeepSeek V4.1 Flash at high.

Yet every time I compare the two in something like Pi, Sol ends up being 5-10x the price for a simple query, something like 7-10c vs. less than 0.5c for DeepSeek. What's the deal?

▲blackoil 2 hours ago | parent [-]

Same for me coding tasks taking $20-50 are easily done by deepseek in $5-10