Inference

BioMysteryBench Human Solvable

Computational biology challenges that independent human experts were able to solve.

  • Not in index
  • Knowledge
ModelsModels with a result.4
Top resultBest result on this test.N/A
Top-3 spreadPoints from first to third.N/A
YearYear of release.N/A

Results

4 results
#ModelResultThe score from the source.
—Claude Opus 590.1%
—Claude Opus 5.589.3%
—Gemini 3.8 Flash88.8%
—Gemini 3.7 Flash87.1%