Phage-plasmid Co-evolution
GPT-6 Luna 10.7 leads since Oct 2026 Only in system cards
Models predict future amino acid mutations in a phage and plasmid system from earlier observations. Scored as negative log likelihood.
OpenAI Critical bio capability evaluation. The Critical threshold is 9.40 or lower.
Made by OpenAI Released Sep 2026 Genomics and life sciences Tasks kept private Last in a system card Oct 2026
Last model added Oct 2026
- Level
- Research frontier Researchers, on open problems or tasks that take days
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Prediction Probabilities for events that have not happened yet.
5
Models scored in lab cards
7
System cards report it, from 1 lab
GPT-6 Luna leads with 10.7
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-6 Luna 10.7
- 2 GPT-6.1 Terra 10.8
- 3 GPT-6 Sol 12.9
- 4 GPT-6.1 Sol 12.9
- 5 GPT-6 Astra 13.1
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Luna | 10.7 | Oct 2026 | Model card | |
| 2 | GPT-6.1 Terra | 10.8 | Oct 2026 | Model card | |
| 3 | GPT-6 Sol | 12.9 | Sep 2026 | Model card | |
| 4 | GPT-6.1 Sol | 12.9 | Sep 2026 | Model card | |
| 5 | GPT-6 Astra | 13.1 | Sep 2026 | Model card |
3 models have held number one since its release in Sep 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
OpenAI
Scores over time
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
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.
7 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 |
|---|---|---|---|---|
| 29 Oct 2026 | GPT-6 Luna system card addendum | 11.8 | Phage–plasmid Co-evolution, negative log-likelihood, lower is better (Table 9) | Bio and chem risk |
| 26 Oct 2026 | GPT-6.1 Terra system card addendum | 10.8 | Phage–plasmid Co-evolution, pooled exact-mutation negative log-likelihood, lower is better (table, 9.0.1.2) | Bio and chem risk |
| 7 Oct 2026 | GPT-6 Sol system card addendum | 12.9 | Phage–plasmid Co-evolution, negative log-likelihood, lower is better (Table 9) | Bio and chem risk |
| 7 Oct 2026 | GPT-6 Luna system card addendum | 10.7 | Phage–plasmid Co-evolution, negative log-likelihood, lower is better (Table 9) | Bio and chem risk |
| 29 Sep 2026 | GPT-6.1 Sol system card addendum | 12.9 | Phage–plasmid Co-evolution, negative log-likelihood, lower is better (9.1.1.2) | Bio and chem risk |
| 22 Sep 2026 | GPT-6 Sol system card | 12.9 | Phage–plasmid Co-evolution, negative log-likelihood, lower is better (Table 34, A.8.1.1.2) | Bio and chem risk |
| 3 Sep 2026 | GPT-6 Astra system card | 13.1 | Phage–plasmid Co-evolution, NLL, lower is better (table shows helpful-only 12.58) (10.1.1.2.4, Table 15) | 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%