Skip to content
Read the original: Perplexity· perplexity_ai·Published· 2d agoAI score34

In agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next ColBERT model, with fewer searches than any baseline.

In agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next...

AISummary

In agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next ColBERT model, with fewer searches than any baseline.

Read the original x.com

Source: Perplexity · x.com

AI agentsPapers & researchEvals & benchmarks#Paper/Research#Eval/Benchmark#RAG#Search#Agent