BlogLLM Benchmark Scores as Published, Side by Side
BioSecBench: Results as Published
Every result the catalog holds for BioSecBench: 4 models from 3 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area BiosecurityMaintainer LatchBioIntroduced 2026Data version 2026103001, as of 2026-10-30
BioSecBench is a family of three checkable tests from LatchBio for AI agents doing biology work with a biosecurity angle. The Refusal part pairs routine research tasks with tasks that look like research but hide a hazard, and measures how often an agent refuses. The Surveillance part checks whether an agent can run pathogen genomic surveillance analyses correctly, and the Function part checks whether an agent can infer biological function from experimental data, scored against ground truth.
BioSecBench Function
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 46% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Claude Opus 5Anthropic, released 2026-07-24 | 44.8% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Grok 4.7xAI, released 2026-09-21 | 43.3% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: xhigh |
| Grok 4.6xAI, released 2026-08-12 | 39.9% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
BioSecBench Refusal
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 25.5% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Claude Opus 5Anthropic, released 2026-07-24 | 31.8% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Grok 4.7xAI, released 2026-09-21 | 62.4% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: xhigh |
| Grok 4.6xAI, released 2026-08-12 | 45.6% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
BioSecBench Surveillance
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 35.2% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Claude Opus 5Anthropic, released 2026-07-24 | 43.6% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: max |
| Grok 4.7xAI, released 2026-09-21 | 48% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: xhigh |
| Grok 4.6xAI, released 2026-08-12 | 48% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.