Benchmark Almanac

Autointent-Bio

Grok 4.6 100% leads since August 2026
Only in system cards

Models face manual and synthetic dangerous and benign biology queries. xAI reports refusal recall on the dangerous ones.

In-house xAI evaluation, run with the full safeguard stack.

Made by
xAI (SpaceXAI)
Released
July 2026
Kind
Hazardous knowledge
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
3
Models scored in lab cards
3
System cards report it, from 1 lab

2 models share the top score of 100% among models released by September 2026

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.

The newest model with a score here came out in September 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 100.0 Grok 4.6
  2. 100.0 Grok 4.7
  3. 97.9 Grok 4.5
  1. 1 Grok 4.6 100%
  2. 2 Grok 4.7 100%
  3. 3 Grok 4.5 97.9%

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Grok 4.6 100% Aug 2026 Lab model card
2 Grok 4.7 100% Sep 2026 Lab model card
3 Grok 4.5 97.9% Jul 2026 Lab model card

2 models have held number one in labs’ own numbers since its release in July 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

xAI
Lab claims Passed 85% in Jul 2026, by Grok 4.5
Grok 4.6 100%

Source: Labs’ model cards

XAI’s own number for Grok 4.5 passed 85% in July 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 4.6 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Grok 4.6

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.

3 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 100 Bio refusal recall (Autointent-Bio), high (9.3 table) Safety
Aug 12, 2026 Grok 4.6 model card 100 Bio refusal recall (Autointent-Bio), high (10.3 table) Safety
Jul 14, 2026 Grok 4.5 model card 97.9 Bio refusal accuracy (Autointent-Bio), full safeguards, high (10.3 table) Safety

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%