Fusion Models Outperform Frontier Labs on Deep Research Benchmark
Reactions from ranked influencers
3 posts
UPDATE: ~6 weeks ago... frontier AI labs lost the "deep research" frontier 4 startups and Los Alamos National Lab have made analogous observations. at @openminedorg we just re-ran @OpenRouter's experiment ourselves. a month after the initial finding, the top 5 AI systems are *still* fusions. the best single model from a frontier AI lab... open or closed source... came 6th. (this is on DRACO... a deep research benchmark... more benchmarks to come) congrats to @siddhant230 and @khoaguin for the great work. more details below 👇
This is a *way* bigger deal than it seems... Frontier AI companies will *never* own the frontier again I kid you not... I've been waiting for someone to show this result for like 4 years... this is a huge deal. The short reason: combinations of models will *always* outperform individual models The long reason: this is the gateway to a million times more data... and huge leaps in compute efficiency. The AI scaling laws always win. More in article below 👇
UPDATE: ~6 weeks ago... frontier AI labs lost the "deep research" frontier 4 startups and Los Alamos National Lab have made analogous observations. at @openminedorg we just re-ran @OpenRouter's experiment ourselves. a month after the initial finding, the top 5 AI systems are *still* fusions. the best single model from a frontier AI lab... open or closed source... came 6th. (this is on DRACO... a deep research benchmark... more benchmarks to come) congrats to @siddhant230 and @khoaguin for the great work. more details below 👇