SecureBio VMQA, single choice
Gemini 3 Pro 61.2% leads since Nov 2025 Only in system cards Models answer 350 virology troubleshooting questions in single-choice form. VMQA is an earlier version of the Virology Capabilities Test.
Google FSF sections report it with N=350. The Gemini 3 Pro FSF report calls the same N=350 set SecureBio VCT SC.
- Level
- Expert Specialists with years of training, often over hours of work
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
Gemini 3 Pro leads with 61.2% among models released by Nov 2025
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 Nov 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Gemini 3 Pro 61.2%
- 2 Gemini 2.5 Pro Jun 2025 56%
- 3 Gemini 2.5 Pro Mar 2025 50.8%
- 4 Gemini 2.5 Flash Jun 2025 48%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 3 Pro | 61.2% | Nov 2025 | Model card | |
| 2 | Gemini 2.5 Pro Jun 2025 | 56% | Jul 2025 | Model card | |
| 3 | Gemini 2.5 Pro Mar 2025 | 50.8% | Apr 2025 | Model card | |
| 4 | Gemini 2.5 Flash Jun 2025 | 48% | Jul 2025 | Model card |
3 models have held number one since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
4 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.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 18 Nov 2025 | Gemini 3 Pro system card | 61.2 | SecureBio VCT - SC (N=350), mean solve rate, shuffled answer choices (Figure 1). Same N=350 single-choice set that earlier Google reports call SecureBio VMQA - SC | Bio and chem risk |
| 7 Jul 2025 | Gemini 2.5 Pro technical report | 56 | SecureBio VMQA - SC (N=350), mean solve rate over 100 shuffled runs (Figure 9) | Bio and chem risk |
| 7 Jul 2025 | Gemini 2.5 Flash technical report | 48 | SecureBio VMQA - SC (N=350), mean solve rate over 100 shuffled runs (Figure 9) | Bio and chem risk |
| 28 Apr 2025 | Gemini 2.5 Pro model card | 50.8 | SecureBio VMQA - SC (N=350), mean solve rate over 100 shuffled runs (Figure 1) | Bio and chem risk |
More in Biology and chemistry
- 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% - 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-6 Astra 37.1%
- 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-6 Astra 60.3%
- MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer.
Intern-S2-397B 62.4% - TOMG-Bench In use Models generate molecules from natural language requests in three tasks: molecule editing, molecule optimization and customized generation. Each output is checked for validity and for meeting the requested properties. Intern-S2-397B 66.8%
- BABE Fading Models reason from experimental results in peer-reviewed biology papers to draw conclusions, with causal and cross-scale inference.
Seed2.0 Lite (0428) 57.9%