Benchmark Almanac

BioUseBench

Grok 4.7 91.4%
Only in system cards

Models face dual-use biology enablement prompts. The reported metric is the refusal rate on the severity 5 subset.

In-house xAI evaluation. Items span virology, wet lab methods, chemical synthesis, toxicology and lab safety.

Made by
xAI (SpaceXAI)
Released
August 2026
Kind
Hazardous knowledge
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
Kept private
Strongest model tested
Grok 4.6 #28 on the capability index
Last in a system card
September 2026
Last model added
September 2026
2
Models scored in lab cards
2
System cards report it, from 1 lab

Grok 4.7 leads with 91.4%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 91.4 Grok 4.7
  2. 90.7 Grok 4.6
  1. 1 Grok 4.7 91.4%
  2. 2 Grok 4.6 90.7%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Grok 4.7 91.4% Sep 2026 Lab model card
2 Grok 4.6 90.7% Aug 2026 Lab model card

XAI’s own number for Grok 4.6 passed 85% in August 2026

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Grok 4.7 Grok 4.6 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Grok 4.7

Source: Labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.

2 system cards report it, from 1 lab

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

DateDocumentScoreAs the document writes itSection
Sep 21, 2026 Grok 4.7 model card 91.4 BioUseBench, dual-use refusal rate on severity-5 subset, high (7.4) Bio and chem risk
Aug 12, 2026 Grok 4.6 model card 90.7 BioUseBench, dual-use refusal rate on severity-5 subset, high (8.3) Bio and chem risk

More in Biology and chemistry

All 109 in Biology and chemistry
  • GeneBench Pro In use Agents analyze messy simulated genomics and biology datasets to estimate a decision-relevant quantity across 129 problems. Scored automatically against known answers. GPT-5.6 Sol 31.5%
  • SUPERChem In use Models solve 500 expert-written chemistry reasoning problems, offered in multimodal and text-only forms. Expert solution paths also allow a reasoning path score. Tencent Hy4 preview 66.4%
  • LifeSciBench In use Models complete 750 expert-written life science research tasks, often with attached figures, tables, or sequence files. Graded against expert rubrics as score and pass rate. GPT-Rosalind-6 61.3%
  • MedChemBench (OpenAI) In use Models answer chemistry questions from an OpenAI internal set, grouped with OpenAI's life science research evaluations. OpenAI has not published the task format. GPT-Rosalind-6 49.6%
  • ProtocolQA Open-Ended In use Models correct errors in published lab protocols using open-ended questions adapted from LAB-Bench ProtocolQA. Scored as pass@1. GPT-6 Cyber 47.2%
  • MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. gpt-oss-120b 47.5%