cd/entity/BenchBench-Protocol· home entities BenchBench-Protocol
grep -l @benchbench-protocol /news/*.json | wc -l → 1

BenchBench-Protocol

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

00:58
2026-08-15
benchling.com
artificial-intelligence

Can LLMs work in the wet lab?

Benchling released BenchBench-Protocol, a benchmark built from thousands of real-world experiments, showing that Anthropic's Opus 5 leads at 59.2%, followed by OpenAI's GPT 5.6 at 47.1%, and open-sour…

// co-occurs with top 6 entities
// topics top 4 topics