BenchBench-Protocol

What is BenchBench-Protocol?

Evaluates LLMs on 149 protocol-modification tasks reconstructed from real changes scientists made to published wet-lab protocols, using weighted rubric scoring.

Released

2026-08-24

Evaluates

General AI, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.23898

BenchBench-Protocol paper

• Paper https://arxiv.org/abs/2608.23898

Which sources cite BenchBench-Protocol?

• BenchBench-Protocol

Related General AI, Language & Knowledge, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ABC-Bench