Can the agent read a messy lab bench?
OpenAI and Ligo published BioBasicsBench, 100 tasks about raw wet-lab evidence, including the times the data cannot support a conclusion. It scores agents. It does not hand you a lab partner.
- Verdict
- Watch Promising, but something is missing: access, pricing, or proof.
- For
- people evaluating lab agents, not people running a bench
- Why it matters
- The benchmark scores agents on raw wet-lab evidence. It does not give you a lab partner.
- Next check
- Recheck if a lab tool you already use publishes a score on this benchmark.
- Published
- By
- The Loaded Tokens desk
- Topic
- Search & research
- Sources
- OpenAI
Sources & limits: This is our recap, not a copy of the original. The links above are the pages we read. We didn't test it ourselves. How we verify
Corrections: if a fact is wrong, email hello@loadedtokens.com.