On Wednesday, @solana introduced Solana Bench, for testing AI’s ability to generate Solana transactions. The verdict: it’s pretty good for things like core Solana transactions & Jupiter swaps. So we decided to show you how you can make it effortless for LLMs like Claude Code to
How well can LLMs actually build transactions on Solana? Until now, there wasn’t a simple, reproducible way to measure. Introducing Solana Bench — open benchmarks for testing AI’s operational competence on Solana. Mega-thread 🧵
7
14
39
Replies
2/ APIs for dozens of key actions across Solana's top protocols, & an MCP server to interact with them:
0
0
5