OpenAI · Tacit Labs

LifeSciBench: Realistic, Expert-Level Life Science Tasks

OpenAI's 750 expert-authored tasks spanning 7 scientific workflows × 7 life-science domains, each with an expert rubric — built to capture the ambiguity and judgment calls that knowledge-QA benchmarks miss (complex artifacts, situational ambiguity, open-ended answers). Far from saturated: no model passes 22.8% of tasks, and 34.8% have a best-model pass rate under 20%. Score shown is the problem-weighted normalized rubric score; top pass rate is 36.1% (GPT-Rosalind).

life-sciencesresearch-workflowstextimagesequencemolecular-structure
Status
curated
Saturation
unsaturated
Runnable
no
Cost to run
high

Editor's note

OpenAI's 750 expert-authored tasks spanning 7 scientific workflows × 7 life-science domains, each with an expert rubric — built to capture the ambiguity and judgment calls that knowledge-QA benchmarks miss (complex artifacts, situational ambiguity, open-ended answers). Far from saturated: no model passes 22.8% of tasks, and 34.8% have a best-model pass rate under 20%. Score shown is the problem-weighted normalized rubric score; top pass rate is 36.1% (GPT-Rosalind).

Results

ModelScoreVariantProvenance
GPT-Rosalind57.6% norm. rubricdefaultpaper
GPT-5.551.9% norm. rubricdefaultpaper
Gemini 3.1 Pro51.5% norm. rubricdefaultpaper
GPT-5.447.9% norm. rubricdefaultpaper
Grok 4.339.9% norm. rubricdefaultpaper

Sources

  • paper LifeSciBench preprint (OpenAI · Tacit Labs)