BlogLLM Benchmark Scores as Published, Side by Side
Virology Capabilities Test: Results as Published
Every result the catalog holds for Virology Capabilities Test: 3 models from 1 developer, 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 SecureBioIntroduced 2025Data version 2026103001, as of 2026-10-30
The Virology Capabilities Test is a set of 322 multimodal questions, written with dozens of PhD-level virologists, about troubleshooting complex virology lab protocols. The questions cover factual, tacit and image-based knowledge, and models are scored by accuracy. In the April 2025 paper, expert virologists averaged about 22 percent on questions in their own sub-areas, and the best model listed there scored about 44 percent.
Virology Capabilities Test (VCT)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Grok 4.7xAI, released 2026-09-21 | 63% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
| Grok 4.6xAI, released 2026-08-12 | 67.4% | xAI, Grok 4.7 model cardchecked 2026-10-14 | Effort: high |
| Grok 4.5xAI, released 2026-07-16 | 65.5% | 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.