LABBench2: An Improved Benchmark for AI Systems Performing Biology Research

A benchmark of realistic biology-research tasks involving literature, figures, tables, databases, and bioinformatics files.

ModelsModels with a result.6
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.2026

Result and price

020406080100$3$10$30RESULTOUTPUT PRICE PER 1M TOKENS · LOG SCALE

Results

6 results
#ModelResultThe score from the source.
GPT-5.6 Sol82.1%