Posts Tagged with “benchmarks”

Benchmarking Lightpanda’s native agent

We learned that an agent’s tools matter more than its engine. We rebuilt our tool surface: the MCP is now far faster and more accurate, and a native agent built into the binary is faster still.Read More →

How should we benchmark Lightpanda for AI agents?

We ran Lightpanda, agent-browser, and browser-use through AssistantBench and GAIA Level 1 with Claude Sonnet 4.6 as the brain. The tool surface mattered more than the engine.Read More →