Human Pathogen Capabilities Test
Models answer expert-level questions on human pathogens from SecureBio. Scored as accuracy.
100 text-only questions with a private holdout. 13 PhD virologists scored about 31%. Modeled after VCT. A v2 exists on the SecureBio dashboard.
- 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
GPT-5.6 Sol leads with 68.4%
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 GPT-5.6 Sol 68.4%
- 2
Muse Wonder Full 66.5% - 3 GPT-6 Astra 65.9%
- 4 Muse Spark 1.3 62.7%
- 5 Muse Spark 1.1 61.9%
- 6 Muse Spark 55.7%
- 7 GPT-5 53.7%
- 8 Code World Model (CWM) 31.2%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.6 Sol | 68.4% | Jun 2026 | Model card | |
| 2 | Muse Wonder Full | 66.5% | Oct 2026 | Model card | |
| 3 | GPT-6 Astra | 65.9% | Sep 2026 | Model card | |
| 4 | Muse Spark 1.3 | 62.7% | Oct 2026 | Model card | |
| 5 | Muse Spark 1.1 | 61.9% | Jul 2026 | Model card | |
| 6 | Muse Spark | 55.7% | Jun 2026 | Model card | |
| 7 | GPT-5 | 53.7% | Aug 2025 | Model card | |
| 8 | Code World Model (CWM) | 31.2% | Oct 2025 | Model card |
3 models have held number one since its release in Aug 2025
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.
9 system cards report it, from 2 labs
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 |
|---|---|---|---|---|
| 23 Oct 2026 | Muse Spark 1.3 system card | 62.7 | HPCT accuracy, Muse Spark 1.3 (API) max (Table 1, Figure 1) | Bio and chem risk |
| 12 Oct 2026 | Muse Wonder Full model card | 66.5 | SecureBio HPCT (CBRN Capability Evaluations table, section 4) | Bio and chem risk |
| 3 Sep 2026 | GPT-6 Astra system card | 65.9 | SecureBio Human Pathogen Capabilities Test (HPCT), refusal-corrected accuracy (10.1.1.4) | Bio and chem risk |
| 9 Jul 2026 | GPT-5.6 Sol system card | 68.4 | SecureBio Human Pathogen Capabilities Test, strongest reported configuration (9.1.1.8) | Bio and chem risk |
| 9 Jul 2026 | Muse Spark 1.1 system card | 61.9 | HPCT, Muse Spark 1.1 Helpful (Table 1, Figure 1) | Bio and chem risk |
| 25 Jun 2026 | GPT-5.6 Sol system card | 68.4 | SecureBio Human Pathogen Capabilities Test, strongest reported configuration (9.1.1.8) | Bio and chem risk |
| 12 Jun 2026 | Muse Spark system card | 55.7 | HPCT (Table 1, Figure 1) | Bio and chem risk |
| 8 Oct 2025 | Code World Model (CWM) technical report | 31.2 | HPCT, multiple response (Table 13) | Bio and chem risk |
| 7 Aug 2025 | GPT-5 system card | 53.7 | SecureBio Human Pathogen Capabilities Test, mean of n=10 (Table 15) | Bio and chem risk |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
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%