LAB-Bench: leaderboard

Language Agent Biology Benchmark for practical biology research tasks, including ProtocolQA, SeqQA, literature/database QA, figure/table reasoning, and hard molecular cloning scenarios relevant to dual-use capability assessment.

Source: huggingface.co.

Interactive version: theaggregate.ai/benchmark?slug=lab-bench · How It Works · Data refreshed daily, snapshot 2026-09-05.