I’m making my way through the GPT-6.2 system card this weekend. Specifically focusing on the biological capabilities described on pages 7-22 of the PDF. Some interesting evals in here that I hadn’t seen before.
Can a model predict if an experiment will support a hypothesis?
Bio-Probe is an internal, exploratory OpenAI evaluation that tests whether a model can predict which biological research hypotheses an experiment will support. We use this task to explore whether a model could help researchers decide which hypotheses to test. We collected 21 private experimental results from seven academics that they tested in 2025 or 2026 and have not yet shared publicly. In each trial, the model receives experimental context and a hypothesis, then estimates the probability that the experiment supports it.
⁂
Can a model to develop new computational biology methods?
EUREKA-Bench is an internal, exploratory OpenAI evaluation that tests whether a model can develop and implement new methods for prediction tasks in computational biology. Open-ended scientific creativity could be a gateway to threat-relevant avenues of research that are hard to anticipate. We believe that measuring the propensity of a model to develop approaches that exhibit strong object-level performance on a verifiable task, while showing a high degree of novelty, is a useful proxy for this capability. This evaluation measures how accurately the method predicts held-out results and grades the novelty of the approach separately. Tasks span enzyme function, molecular properties, protein stability, gene regulation, and phage–host interactions.
⁂
How much of a (simulated) wet-lab workflow can the model do out on its own?
Sequitur Research’s exploratory lab automation evaluation measures how much of a simulated wet-lab workflow GPT-6.2 Astra can carry out on its own. […] The model was asked, in simulation, to modify the DNA of three benign proxy organisms and design a two-tiered assessment to validate its initial findings. The task would span multiple weeks of lab work and required the model to design the experiment, operate instruments, handle samples, recover from experimental mistakes, and interpret data. Once a run started, the model received no further steering. The simulation assumed a well-resourced and advanced facility, containing several resources that the model could use as support. […] We do not yet have an indicative threshold for what would constitute concerning uplift.
⁂
There was another interesting new red-teaming approach to novel biothreat development described at the end of the chem/bio section.
For GPT-6.2 Astra, we also piloted a new red-teaming of novel-threat ideation by inviting two leading experts in pandemic science to use a railfree model to attempt to elicit non-public sensitive information about existing and novel biothreats. They were instructed to see if they could elicit this information using minimal and open-ended prompts, simulating the early stages of an adversary lacking specialized knowledge searching for dangerous ideas to pursue. This elicitation exercise was conducted in a secure environment with strong information security controls and no sharing of details beyond the testing group. Publishing specific findings from this exercise could itself pose a safety risk by drawing attention to harmful biological insights. However, an overall verdict from the experts in their internal report was that: “[GPT-6.2 Astra] shows weakness in our tests of open-ended biological threat ideation. The model struggles to combine known biological concepts in a way that results in creative or novel biothreat scenarios.”
