Question 1

What is the best LLM for agents and tool use?

Accepted Answer

Claude Sonnet 5.5 from Anthropic ranks first (agents score 78.1), followed by GPT-6 Astra (77.0) and Claude Opus 5.5 (76.9). Ranked by the Respan Index agents score, which combines agent benchmarks such as OSWorld-Verified, tau2-bench, Toolathlon and APEX-Agents. Only models with published agent results are ranked.

Question 2

How is this ranking made?

Accepted Answer

Ranked by the Respan Index agents score, which combines agent benchmarks such as OSWorld-Verified, tau2-bench, Toolathlon and APEX-Agents. Only models with published agent results are ranked. The Respan Index combines published benchmark results, each linked to its source, and is updated as new results come out.

Question 3

Can I use these models through one API?

Accepted Answer

Yes. The Respan gateway serves models from every major provider behind one OpenAI-compatible API, with fallbacks when a provider fails.

Models

Models

Best LLM for agents and tool use

FAQ

Best model for other jobs