I wonder if search engines linked to human-use-case engines (e.g. google/bing) start at a disadvantage because they have been historically incentivized to break themselves to support their business models? It seems reasonable to suppose that "good at selling ads" ≠ "good at finding results".

do you somehow control how non-trivial the queries are? The LLM generates them, right?

what if every engine returns garbage, or on the other hand, handles them too well?

building a benchmark like this in a genuinely fair way seems extremely hard to me. I’m very curious about the details, of course within what you can share.

One of the authors here. We have been seeing lots of benchmaxxing and leakage in standard web search benchmarks such as BrowseComp.

We developed this live benchmark with daily/hourly sampled fresh queries matching real agentic search traffic to estimate actual search performance of different AI search providers.

so is this an independent search engine benchmark or a blog post from a search engine provider showing their search engine at the top of the benchmark?

i'm a little bit confused as at first when I was reading it i thought it was a search engine benchmark, but it seems that keenable is at the top which i assume is related to the web domain owner? i've never heard of keeenable

Do you think it will be possible to train on this bench?

The blog post appears to get confused and devotes its entire second half to pitching Keenable itself. If the idea is to build credibility for the new benchmark, this maybe was not the best choice.

    Search engines with their own indexes can retrieve documents no one else has. That means your agents will be able to answer questions previously unanswerable.

    Search engines should improve from being used in a way where the quality improvement is not an engineering push but a property of the architecture. That's a learning machine, and it's the only kind of system that can adapt to agents.

[flagged]