Agents
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 Co…
In agentic search, a GPT‑OSS‑120B agent employing the 9B model achieves a 64.0 % accuracy on BrowseComp+ questions. This performance is 4.9 points higher than the next best ColBERT model and requires
In agentic search, a GPT‑OSS‑120B agent employing the 9B model achieves a 64.0 % accuracy on BrowseComp+ questions. This performance is 4.9 points higher than the next best ColBERT model and requires fewer searches than any baseline approach.
Related
- 1/5 We hit SOTA performance on BrowseComp-Plus with 95.18% accuracy using AI21 Maestro’s agent optimization. Here’s how we automated the sea…
- More info about Search as Code in the Perplexity Agent API docs: https://docs.perplexity.ai/docs/agent-api/tools/sandbox
- SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs
Source: Perplexity (X) | 2026-10-07