Benchmarks

GeneBench-Pro

Benchmark · From OpenAI · 1 item since Jul 2026

Judgment-heavy computational-biology tasks testing end-to-end genomics analysis.

Items

  1. Jun 30

    OpenAI's GeneBench-Pro

    A deterministically graded benchmark of 129 judgment-heavy computational-biology tasks on which the strongest model, GPT-5.6 Sol, passes only 28.7% (31.5% with Pro), versus under 5% for GPT-5 when the original GeneBench launched.